1
|
Oikonomou EK, Holste G, Yuan N, Coppi A, McNamara RL, Haynes NA, Vora AN, Velazquez EJ, Li F, Menon V, Kapadia SR, Gill TM, Nadkarni GN, Krumholz HM, Wang Z, Ouyang D, Khera R. A Multimodal Video-Based AI Biomarker for Aortic Stenosis Development and Progression. JAMA Cardiol 2024:2817468. [PMID: 38581644 PMCID: PMC10999005 DOI: 10.1001/jamacardio.2024.0595] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/28/2023] [Accepted: 02/27/2024] [Indexed: 04/08/2024]
Abstract
Importance Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up. A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler characterization. Objective To deploy DASSi to patients with no AS or with mild or moderate AS at baseline to identify AS development and progression. Design, Setting, and Participants This is a cohort study that examined 2 cohorts of patients without severe AS undergoing echocardiography in the Yale New Haven Health System (YNHHS; 2015-2021) and Cedars-Sinai Medical Center (CSMC; 2018-2019). A novel computational pipeline for the cross-modal translation of DASSi into cardiac magnetic resonance (CMR) imaging was further developed in the UK Biobank. Analyses were performed between August 2023 and February 2024. Exposure DASSi (range, 0-1) derived from AI applied to echocardiography and CMR videos. Main Outcomes and Measures Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR). Results A total of 12 599 participants were included in the echocardiographic study (YNHHS: n = 8798; median [IQR] age, 71 [60-80] years; 4250 [48.3%] women; median [IQR] follow-up, 4.1 [2.4-5.4] years; and CSMC: n = 3801; median [IQR] age, 67 [54-78] years; 1685 [44.3%] women; median [IQR] follow-up, 3.4 [2.8-3.9] years). Higher baseline DASSi was associated with faster progression in AV-Vmax (per 0.1 DASSi increment: YNHHS, 0.033 m/s per year [95% CI, 0.028-0.038] among 5483 participants; CSMC, 0.082 m/s per year [95% CI, 0.053-0.111] among 1292 participants), with values of 0.2 or greater associated with a 4- to 5-fold higher AVR risk than values less than 0.2 (YNHHS: 715 events; adjusted hazard ratio [HR], 4.97 [95% CI, 2.71-5.82]; CSMC: 56 events; adjusted HR, 4.04 [95% CI, 0.92-17.70]), independent of age, sex, race, ethnicity, ejection fraction, and AV-Vmax. This was reproduced across 45 474 participants (median [IQR] age, 65 [59-71] years; 23 559 [51.8%] women; median [IQR] follow-up, 2.5 [1.6-3.9] years) undergoing CMR imaging in the UK Biobank (for participants with DASSi ≥0.2 vs those with DASSi <.02, adjusted HR, 11.38 [95% CI, 2.56-50.57]). Saliency maps and phenome-wide association studies supported associations with cardiac structure and function and traditional cardiovascular risk factors. Conclusions and Relevance In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker was independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.
Collapse
Affiliation(s)
- Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Gregory Holste
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin
| | - Neal Yuan
- Department of Medicine, University of California, San Francisco
- Division of Cardiology, San Francisco Veterans Affairs Medical Center, San Francisco, California
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale New Haven Hospital, New Haven, Connecticut
| | - Robert L. McNamara
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Norrisa A. Haynes
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Amit N. Vora
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Eric J. Velazquez
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Fan Li
- Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut
- Center for Methods in Implementation and Prevention Science, Yale School of Public Health, New Haven, Connecticut
| | - Venu Menon
- Heart and Vascular Institute, Department of Cardiovascular Medicine, Cleveland Clinic Foundation, Cleveland, Ohio
| | - Samir R. Kapadia
- Heart and Vascular Institute, Department of Cardiovascular Medicine, Cleveland Clinic Foundation, Cleveland, Ohio
| | - Thomas M. Gill
- Section of Geriatrics, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Girish N. Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
- Center for Outcomes Research and Evaluation, Yale New Haven Hospital, New Haven, Connecticut
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin
| | - David Ouyang
- Smidt Heart Institute, Department of Cardiology, Cedars-Sinai Medical Center, Los Angeles, California
- Division of Artificial Intelligence in Medicine, Cedars-Sinai Medical Center, Los Angeles, California
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
- Center for Outcomes Research and Evaluation, Yale New Haven Hospital, New Haven, Connecticut
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, Connecticut
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut
- Associate Editor, JAMA
| |
Collapse
|
2
|
Dhingra LS, Aminorroaya A, Sangha V, Camargos AP, Asselbergs FW, Brant LCC, Barreto SM, Ribeiro ALP, Krumholz HM, Oikonomou EK, Khera R. Scalable Risk Stratification for Heart Failure Using Artificial Intelligence applied to 12-lead Electrocardiographic Images: A Multinational Study. medRxiv 2024:2024.04.02.24305232. [PMID: 38633808 PMCID: PMC11023679 DOI: 10.1101/2024.04.02.24305232] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/19/2024]
Abstract
Background Current risk stratification strategies for heart failure (HF) risk require either specific blood-based biomarkers or comprehensive clinical evaluation. In this study, we evaluated the use of artificial intelligence (AI) applied to images of electrocardiograms (ECGs) to predict HF risk. Methods Across multinational longitudinal cohorts in the integrated Yale New Haven Health System (YNHHS) and in population-based UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), we identified individuals without HF at baseline. Incident HF was defined based on the first occurrence of an HF hospitalization. We evaluated an AI-ECG model that defines the cross-sectional probability of left ventricular dysfunction from a single image of a 12-lead ECG and its association with incident HF. We accounted for the competing risk of death using the Fine-Gray subdistribution model and evaluated the discrimination using Harrel's c-statistic. The pooled cohort equations to prevent HF (PCP-HF) were used as a comparator for estimating incident HF risk. Results Among 231,285 individuals at YNHHS, 4472 had a primary HF hospitalization over 4.5 years (IQR 2.5-6.6) of follow-up. In UKB and ELSA-Brasil, among 42,741 and 13,454 people, 46 and 31 developed HF over a follow-up of 3.1 (2.1-4.5) and 4.2 (3.7-4.5) years, respectively. A positive AI-ECG screen portended a 4-fold higher risk of incident HF among YNHHS patients (age-, sex-adjusted HR [aHR] 3.88 [95% CI, 3.63-4.14]). In UKB and ELSA-Brasil, a positive-screen ECG portended 13- and 24-fold higher hazard of incident HF, respectively (aHR: UKBB, 12.85 [6.87-24.02]; ELSA-Brasil, 23.50 [11.09-49.81]). The association was consistent after accounting for comorbidities and the competing risk of death. Higher model output probabilities were progressively associated with a higher risk for HF. The model's discrimination for incident HF was 0.718 in YNHHS, 0.769 in UKB, and 0.810 in ELSA-Brasil. Across cohorts, incorporating model probability with PCP-HF yielded a significant improvement in discrimination over PCP-HF alone. Conclusions An AI model applied to images of 12-lead ECGs can identify those at elevated risk of HF across multinational cohorts. As a digital biomarker of HF risk that requires just an ECG image, this AI-ECG approach can enable scalable and efficient screening for HF risk.
Collapse
Affiliation(s)
- Lovedeep S Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Department of Engineering Science, University of Oxford, Oxford, UK
| | - Aline Pedroso Camargos
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Folkert W Asselbergs
- Department of Cardiology, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
- Institute of Health Informatics, University College London, London, UK
- The National Institute for Health Research University College London Hospitals Biomedical Research Centre, University College London, London, UK
| | - Luisa CC Brant
- Department of Internal Medicine, Faculdade de Medicina, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
- Telehealth Center and Cardiology Service, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
| | - Sandhi M Barreto
- Department of Preventive Medicine, School of Medicine, Faculdade de Medicina, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
| | - Antonio Luiz P Ribeiro
- Department of Internal Medicine, Faculdade de Medicina, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
- Telehealth Center and Cardiology Service, Hospital das Clínicas, Universidade Federal de Minas Gerais, Belo Horizonte, Brazil
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
| |
Collapse
|
3
|
Sangha V, Khunte A, Holste G, Mortazavi BJ, Wang Z, Oikonomou EK, Khera R. Biometric contrastive learning for data-efficient deep learning from electrocardiographic images. J Am Med Inform Assoc 2024; 31:855-865. [PMID: 38269618 PMCID: PMC10990541 DOI: 10.1093/jamia/ocae002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/14/2023] [Revised: 12/28/2023] [Accepted: 01/02/2024] [Indexed: 01/26/2024] Open
Abstract
OBJECTIVE Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs). However, traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. MATERIALS AND METHODS Using pairs of ECGs from 78 288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF < 40%, using ECGs from 2015 to 2021. We externally tested the models in cohorts from Germany and the United States. We compared BCL with ImageNet initialization and general-purpose self-supervised contrastive learning for images (simCLR). RESULTS While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF < 40% with an AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (ImageNet) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with an AUROC of 0.88/0.88 for Gender and LVEF < 40% compared with 0.83/0.83 (ImageNet) and 0.84/0.83 (simCLR). DISCUSSION AND CONCLUSION A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.
Collapse
Affiliation(s)
- Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University, New Haven, CT, 06510, United States
- Department of Engineering Science, Oxford University, Oxford, OX1 3PJ, United Kingdom
| | - Akshay Khunte
- Department of Computer Science, Yale University, New Haven, CT, 06511, United States
| | - Gregory Holste
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, 78712, United States
| | - Bobak J Mortazavi
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX, 77843, United States
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, 06510, United States
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, 78712, United States
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University, New Haven, CT, 06510, United States
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University, New Haven, CT, 06510, United States
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, 06510, United States
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, 06510, United States
| |
Collapse
|
4
|
Thangaraj PM, Shankar SV, Huang S, Nadkarni G, Mortazavi B, Oikonomou EK, Khera R. A Novel Digital Twin Strategy to Examine the Implications of Randomized Control Trials for Real-World Populations. medRxiv 2024:2024.03.25.24304868. [PMID: 38585929 PMCID: PMC10996766 DOI: 10.1101/2024.03.25.24304868] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/09/2024]
Abstract
Randomized clinical trials (RCTs) are essential to guide medical practice; however, their generalizability to a given population is often uncertain. We developed a statistically informed Generative Adversarial Network (GAN) model, RCT-Twin-GAN, that leverages relationships between covariates and outcomes and generates a digital twin of an RCT (RCT-Twin) conditioned on covariate distributions from a second patient population. We used RCT-Twin-GAN to reproduce treatment effect outcomes of the Systolic Blood Pressure Intervention Trial (SPRINT) and the Action to Control Cardiovascular Risk in Diabetes (ACCORD) Blood Pressure Trial, which tested the same intervention but had different treatment effect results. To demonstrate treatment effect estimates of each RCT conditioned on the other RCT patient population, we evaluated the cardiovascular event-free survival of SPRINT digital twins conditioned on the ACCORD cohort and vice versa (SPRINT-conditioned ACCORD twins). The conditioned digital twins were balanced by the intervention arm (mean absolute standardized mean difference (MASMD) of covariates between treatment arms 0.019 (SD 0.018), and the conditioned covariates of the SPRINT-Twin on ACCORD were more similar to ACCORD than a sprint (MASMD 0.0082 SD 0.016 vs. 0.46 SD 0.20). Most importantly, across iterations, SPRINT conditioned ACCORD-Twin datasets reproduced the overall non-significant effect size seen in ACCORD (5-year cardiovascular outcome hazard ratio (95% confidence interval) of 0.88 (0.73-1.06) in ACCORD vs median 0.87 (0.68-1.13) in the SPRINT conditioned ACCORD-Twin), while the ACCORD conditioned SPRINT-Twins reproduced the significant effect size seen in SPRINT (0.75 (0.64-0.89) vs median 0.79 (0.72-0.86)) in ACCORD conditioned SPRINT-Twin). Finally, we describe the translation of this approach to real-world populations by conditioning the trials on an electronic health record population. Therefore, RCT-Twin-GAN simulates the direct translation of RCT-derived treatment effects across various patient populations with varying covariate distributions.
Collapse
Affiliation(s)
- Phyllis M. Thangaraj
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Sumukh Vasisht Shankar
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Sicong Huang
- Department of Computer Science and Engineering, Texas A&M University, College Station, TX
| | - Girish Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- The Division of Data Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Bobak Mortazavi
- Department of Computer Science and Engineering, Texas A&M University, College Station, TX
| | - Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| |
Collapse
|
5
|
Oikonomou EK, Sangha V, Dhingra LS, Aminorroaya A, Coppi A, Krumholz HM, Baldassarre LA, Khera R. Artificial intelligence-enhanced risk stratification of cancer therapeutics-related cardiac dysfunction using electrocardiographic images. medRxiv 2024:2024.03.12.24304047. [PMID: 38562897 PMCID: PMC10984033 DOI: 10.1101/2024.03.12.24304047] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/04/2024]
Abstract
Background Risk stratification strategies for cancer therapeutics-related cardiac dysfunction (CTRCD) rely on serial monitoring by specialized imaging, limiting their scalability. Objectives To examine an artificial intelligence (AI)-enhanced electrocardiographic (AI-ECG) surrogate for imaging risk biomarkers, and its association with CTRCD. Methods Across a five-hospital U.S.-based health system (2013-2023), we identified patients with breast cancer or non-Hodgkin lymphoma (NHL) who received anthracyclines (AC) and/or trastuzumab (TZM), and a control cohort receiving immune checkpoint inhibitors (ICI). We deployed a validated AI model of left ventricular systolic dysfunction (LVSD) to ECG images (≥0.1, positive screen) and explored its association with i) global longitudinal strain (GLS) measured within 15 days (n=7,271 pairs); ii) future CTRCD (new cardiomyopathy, heart failure, or left ventricular ejection fraction [LVEF]<50%), and LVEF<40%. In the ICI cohort we correlated baseline AI-ECG-LVSD predictions with downstream myocarditis. Results Higher AI-ECG LVSD predictions were associated with worse GLS (-18% [IQR:-20 to -17%] for predictions<0.1, to -12% [IQR:-15 to -9%] for ≥0.5 (p<0.001)). In 1,308 patients receiving AC/TZM (age 59 [IQR:49-67] years, 999 [76.4%] women, 80 [IQR:42-115] follow-up months) a positive baseline AI-ECG LVSD screen was associated with ~2-fold and ~4.8-fold increase in the incidence of the composite CTRCD endpoint (adj.HR 2.22 [95%CI:1.63-3.02]), and LVEF<40% (adj.HR 4.76 [95%CI:2.62-8.66]), respectively. Among 2,056 patients receiving ICI (age 65 [IQR:57-73] years, 913 [44.4%] women, follow-up 63 [IQR:28-99] months) AI-ECG predictions were not associated with ICI myocarditis (adj.HR 1.36 [95%CI:0.47-3.93]). Conclusion AI applied to baseline ECG images can stratify the risk of CTRCD associated with anthracycline or trastuzumab exposure.
Collapse
Affiliation(s)
- Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Department of Engineering Science, University of Oxford, Oxford, UK
| | - Lovedeep S. Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
| | - Lauren A. Baldassarre
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT
| |
Collapse
|
6
|
Aminorroaya A, Dhingra LS, Camargos AP, Shankar SV, Khunte A, Sangha V, McNamara RL, Haynes N, Oikonomou EK, Khera R. Study Protocol for the Artificial Intelligence-Driven Evaluation of Structural Heart Diseases Using Wearable Electrocardiogram (ID-SHD). medRxiv 2024:2024.03.18.24304477. [PMID: 38562867 PMCID: PMC10984075 DOI: 10.1101/2024.03.18.24304477] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 04/04/2024]
Abstract
Introduction Portable devices capable of electrocardiogram (ECG) acquisition have the potential to enhance structural heart disease (SHD) management by enabling early detection through artificial intelligence-ECG (AI-ECG) algorithms. However, the performance of these AI algorithms for identifying SHD in a real-world screening setting is unknown. To address this gap, we aim to evaluate the validity of our wearable-adapted AI algorithm, which has been previously developed and validated for detecting SHD from single-lead portable ECGs in patients undergoing routine echocardiograms in the Yale New Haven Hospital (YNHH). Research Methods and Analysis This is the protocol for a cross-sectional study in the echocardiographic laboratories of YNHH. The study will enroll 585 patients referred for outpatient transthoracic echocardiogram (TTE) as part of their routine clinical care. Patients expressing interest in participating in the study will undergo a screening interview, followed by enrollment upon meeting eligibility criteria and providing informed consent. During their routine visit, patients will undergo a 1-lead ECG with two devices - one with an Apple Watch and the second with another portable 1-lead ECG device. With participant consent, these 1-lead ECG data will be linked to participant demographic and clinical data recorded in the YNHH electronic health records (EHR). The study will assess the performance of the AI-ECG algorithm in identifying SHD, including left ventricular systolic dysfunction (LVSD), valvular disease and severe left ventricular hypertrophy (LVH), by comparing the algorithm's results with data obtained from TTE, which is the established gold standard for diagnosing SHD. Ethics and Dissemination All patient EHR data required for assessing eligibility and conducting the AI-ECG will be accessed through secure servers approved for protected health information. Data will be maintained on secure, encrypted servers for a minimum of five years after the publication of our findings in a peer-reviewed journal, and any unanticipated adverse events or risks will be reported by the principal investigator to the Yale Institutional Review Board, which has reviewed and approved this protocol (Protocol Number: 2000035532).
Collapse
Affiliation(s)
- Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Lovedeep Singh Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Aline Pedroso Camargos
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Sumukh Vasisht Shankar
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Akshay Khunte
- Department of Computer Science, Yale University, New Haven, CT, USA
| | - Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Department of Engineering Science, Oxford University, Oxford, OX1 3PJ, United Kingdom
| | - Robert L McNamara
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Norrisa Haynes
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven,Connecticut, USA
| |
Collapse
|
7
|
Oikonomou EK, Holste G, Coppi A, McNamara RL, Nadkarni GN, Baloescu C, Krumholz HM, Wang Z, Khera R. Artificial intelligence-guided detection of under-recognized cardiomyopathies on point-of-care cardiac ultrasound. medRxiv 2024:2024.03.10.24304044. [PMID: 38559021 PMCID: PMC10980112 DOI: 10.1101/2024.03.10.24304044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 04/04/2024]
Abstract
Background Point-of-care ultrasonography (POCUS) enables access to cardiac imaging directly at the bedside but is limited by brief acquisition, variation in acquisition quality, and lack of advanced protocols. Objective To develop and validate deep learning models for detecting underdiagnosed cardiomyopathies on cardiac POCUS, leveraging a novel acquisition quality-adapted modeling strategy. Methods To develop the models, we identified transthoracic echocardiograms (TTEs) of patients across five hospitals in a large U.S. health system with transthyretin amyloid cardiomyopathy (ATTR-CM, confirmed by Tc99m-pyrophosphate imaging), hypertrophic cardiomyopathy (HCM, confirmed by cardiac magnetic resonance), and controls enriched for the presence of severe AS. In a sample of 290,245 TTE videos, we used novel augmentation approaches and a customized loss function to weigh image and view quality to train a multi-label, view agnostic video-based convolutional neural network (CNN) to discriminate the presence of ATTR-CM, HCM, and/or AS. Models were tested across 3,758 real-world POCUS videos from 1,879 studies in 1,330 independent emergency department (ED) patients from 2011 through 2023. Results Our multi-label, view-agnostic classifier demonstrated state-of-the-art performance in discriminating ATTR-CM (AUROC 0.98 [95%CI: 0.96-0.99]) and HCM (AUROC 0.95 [95% CI: 0.94-0.96]) on standard TTE studies. Automated metrics of anatomical view correctness confirmed significantly lower quality in POCUS vs TTE videos (median view classifier confidence of 0.63 [IQR: 0.44-0.88] vs 0.93 [IQR: 0.69-1.00], p<0.001). When deployed to POCUS videos, our algorithm effectively discriminated ATTR-CM and HCM with AUROC of up to 0.94 (parasternal long-axis (PLAX)), and 0.85 (apical 4 chamber), corresponding to positive diagnostic odds ratios of 46.7 and 25.5, respectively. In total, 18/35 (51.4%) of ATTR-CM and 32/57 (41.1%) of HCM patients in the POCUS cohort had an AI-positive screen in the year before their eventual confirmatory imaging. Conclusions We define and validate an AI framework that enables scalable, opportunistic screening of under-diagnosed cardiomyopathies using POCUS.
Collapse
Affiliation(s)
- Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Gregory Holste
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Robert L. McNamara
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Girish N. Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Cristiana Baloescu
- Department of Emergency Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT
| |
Collapse
|
8
|
Oikonomou EK, Khera R. Leveraging the Full Potential of Wearable Devices in Cardiomyopathies. J Card Fail 2024:S1071-9164(24)00067-8. [PMID: 38452997 DOI: 10.1016/j.cardfail.2024.02.011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2024] [Revised: 02/19/2024] [Accepted: 02/20/2024] [Indexed: 03/09/2024]
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT; Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT; Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT. https://twitter.com/rohan_khera
| |
Collapse
|
9
|
Dhingra LS, Sangha V, Aminorroaya A, Bryde R, Gaballa A, Ali AH, Mehra N, Krumholz HM, Sen S, Kramer CM, Martinez MW, Desai MY, Oikonomou EK, Khera R. A Multicenter Evaluation of the Impact of Therapies on Deep Learning-based Electrocardiographic Hypertrophic Cardiomyopathy Markers. medRxiv 2024:2024.01.15.24301011. [PMID: 38293023 PMCID: PMC10827251 DOI: 10.1101/2024.01.15.24301011] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2024]
Abstract
Background Artificial intelligence-enhanced electrocardiography (AI-ECG) can identify hypertrophic cardiomyopathy (HCM) on 12-lead ECGs and offers a novel way to monitor treatment response. While the surgical or percutaneous reduction of the interventricular septum (SRT) represented initial HCM therapies, mavacamten offers an oral alternative. Objective To evaluate biological response to SRT and mavacamten. Methods We applied an AI-ECG model for HCM detection to ECG images from patients who underwent SRT across three sites: Yale New Haven Health System (YNHHS), Cleveland Clinic Foundation (CCF), and Atlantic Health System (AHS); and to ECG images from patients receiving mavacamten at YNHHS. Results A total of 70 patients underwent SRT at YNHHS, 100 at CCF, and 145 at AHS. At YNHHS, there was no significant change in the AI-ECG HCM score before versus after SRT (pre-SRT: median 0.55 [IQR 0.24-0.77] vs post-SRT: 0.59 [0.40-0.75]). The AI-ECG HCM scores also did not improve post SRT at CCF (0.61 [0.32-0.79] vs 0.69 [0.52-0.79]) and AHS (0.52 [0.35-0.69] vs 0.61 [0.49-0.70]). Among 36 YNHHS patients on mavacamten therapy, the median AI-ECG score before starting mavacamten was 0.41 (0.22-0.77), which decreased significantly to 0.28 (0.11-0.50, p <0.001 by Wilcoxon signed-rank test) at the end of a median follow-up period of 237 days. Conclusions The lack of improvement in AI-based HCM score with SRT, in contrast to a significant decrease with mavacamten, suggests the potential role of AI-ECG for serial monitoring of pathophysiological improvement in HCM at the point-of-care using ECG images.
Collapse
Affiliation(s)
- Lovedeep S Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Department of Engineering Science, Oxford University, Oxford, UK
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Robyn Bryde
- Department of Cardiovascular Medicine, Atlantic Health, Morristown Medical Center, Morristown, NJ, USA
- Sports Cardiology and Hypertrophic Cardiomyopathy, Morristown Medical Center, Morristown, NJ, USA
| | - Andrew Gaballa
- Heart, Vascular and Thoracic Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Adel H Ali
- Heart, Vascular and Thoracic Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Nandini Mehra
- Heart, Vascular and Thoracic Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
| | - Sounok Sen
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Christopher M Kramer
- Cardiovascular Division, Department of Medicine, University of Virginia Health, Charlottesville, VA, USA
| | - Matthew W Martinez
- Department of Cardiovascular Medicine, Atlantic Health, Morristown Medical Center, Morristown, NJ, USA
- Sports Cardiology and Hypertrophic Cardiomyopathy, Morristown Medical Center, Morristown, NJ, USA
| | - Milind Y Desai
- Heart, Vascular and Thoracic Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
| |
Collapse
|
10
|
Oikonomou EK, Holste G, Yuan N, Coppi A, McNamara RL, Haynes N, Vora AN, Velazquez EJ, Li F, Menon V, Kapadia SR, Gill TM, Nadkarni GN, Krumholz HM, Wang Z, Ouyang D, Khera R. A Multimodality Video-Based AI Biomarker For Aortic Stenosis Development And Progression. medRxiv 2024:2023.09.28.23296234. [PMID: 37808685 PMCID: PMC10557799 DOI: 10.1101/2023.09.28.23296234] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/10/2023]
Abstract
Importance Aortic stenosis (AS) is a major public health challenge with a growing therapeutic landscape, but current biomarkers do not inform personalized screening and follow-up. Objective A video-based artificial intelligence (AI) biomarker (Digital AS Severity index [DASSi]) can detect severe AS using single-view long-axis echocardiography without Doppler. Here, we deploy DASSi to patients with no or mild/moderate AS at baseline to identify AS development and progression. Design Setting and Participants We defined two cohorts of patients without severe AS undergoing echocardiography in the Yale-New Haven Health System (YNHHS) (2015-2021, 4.1[IQR:2.4-5.4] follow-up years) and Cedars-Sinai Medical Center (CSMC) (2018-2019, 3.4[IQR:2.8-3.9] follow-up years). We further developed a novel computational pipeline for the cross-modality translation of DASSi into cardiac magnetic resonance (CMR) imaging in the UK Biobank (2.5[IQR:1.6-3.9] follow-up years). Analyses were performed between August 2023-February 2024. Exposure DASSi (range: 0-1) derived from AI applied to echocardiography and CMR videos. Main Outcomes and Measures Annualized change in peak aortic valve velocity (AV-Vmax) and late (>6 months) aortic valve replacement (AVR). Results A total of 12,599 participants were included in the echocardiographic study (YNHHS: n=8,798, median age of 71 [IQR (interquartile range):60-80] years, 4250 [48.3%] women, and CSMC: n=3,801, 67 [IQR:54-78] years, 1685 [44.3%] women). Higher baseline DASSi was associated with faster progression in AV-Vmax (per 0.1 DASSi increments: YNHHS: +0.033 m/s/year [95%CI:0.028-0.038], n=5,483, and CSMC: +0.082 m/s/year [0.053-0.111], n=1,292), with levels ≥ vs <0.2 linked to a 4-to-5-fold higher AVR risk (715 events in YNHHS; adj.HR 4.97 [95%CI: 2.71-5.82], 56 events in CSMC: 4.04 [0.92-17.7]), independent of age, sex, ethnicity/race, ejection fraction and AV-Vmax. This was reproduced across 45,474 participants (median age 65 [IQR:59-71] years, 23,559 [51.8%] women) undergoing CMR in the UK Biobank (adj.HR 11.4 [95%CI:2.56-50.60] for DASSi ≥vs<0.2). Saliency maps and phenome-wide association studies supported links with traditional cardiovascular risk factors and diastolic dysfunction. Conclusions and Relevance In this cohort study of patients without severe AS undergoing echocardiography or CMR imaging, a new AI-based video biomarker is independently associated with AS development and progression, enabling opportunistic risk stratification across cardiovascular imaging modalities as well as potential application on handheld devices.
Collapse
Affiliation(s)
- Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Gregory Holste
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Neal Yuan
- Department of Medicine, University of California San Francisco, San Francisco, CA, USA
- Division of Cardiology, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Robert L. McNamara
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Norrisa Haynes
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Amit N. Vora
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Eric J. Velazquez
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Fan Li
- Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
- Center for Methods in Implementation and Prevention Science, Yale School of Public Health, New Haven, CT, USA
| | - Venu Menon
- Department of Cardiovascular Medicine, Heart and Vascular Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Samir R. Kapadia
- Department of Cardiovascular Medicine, Heart and Vascular Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
| | - Thomas M Gill
- Section of Geriatrics, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Girish N. Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- Division of Nephrology, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - David Ouyang
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
- Division of Artificial Intelligence in Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT
- Associate Editor, JAMA
| |
Collapse
|
11
|
Khunte A, Sangha V, Oikonomou EK, Dhingra LS, Aminorroaya A, Coppi A, Shankar SV, Mortazavi BJ, Bhatt DL, Krumholz HM, Nadkarni GN, Vaid A, Khera R. Automated Diagnostic Reports from Images of Electrocardiograms at the Point-of-Care. medRxiv 2024:2024.02.17.24302976. [PMID: 38405776 PMCID: PMC10889032 DOI: 10.1101/2024.02.17.24302976] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/27/2024]
Abstract
Timely and accurate assessment of electrocardiograms (ECGs) is crucial for diagnosing, triaging, and clinically managing patients. Current workflows rely on a computerized ECG interpretation using rule-based tools built into the ECG signal acquisition systems with limited accuracy and flexibility. In low-resource settings, specialists must review every single ECG for such decisions, as these computerized interpretations are not available. Additionally, high-quality interpretations are even more essential in such low-resource settings as there is a higher burden of accuracy for automated reads when access to experts is limited. Artificial Intelligence (AI)-based systems have the prospect of greater accuracy yet are frequently limited to a narrow range of conditions and do not replicate the full diagnostic range. Moreover, these models often require raw signal data, which are unavailable to physicians and necessitate costly technical integrations that are currently limited. To overcome these challenges, we developed and validated a format-independent vision encoder-decoder model - ECG-GPT - that can generate free-text, expert-level diagnosis statements directly from ECG images. The model shows robust performance, validated on 2.6 million ECGs across 6 geographically distinct health settings: (1) 2 large and diverse US health systems- Yale-New Haven and Mount Sinai Health Systems, (2) a consecutive ECG dataset from a central ECG repository from Minas Gerais, Brazil, (3) the prospective cohort study, UK Biobank, (4) a Germany-based, publicly available repository, PTB-XL, and (5) a community hospital in Missouri. The model demonstrated consistently high performance (AUROC≥0.81) across a wide range of rhythm and conduction disorders. This can be easily accessed via a web-based application capable of receiving ECG images and represents a scalable and accessible strategy for generating accurate, expert-level reports from images of ECGs, enabling accurate triage of patients globally, especially in low-resource settings.
Collapse
Affiliation(s)
- Akshay Khunte
- Department of Computer Science, Yale University, New Haven, CT
| | - Veer Sangha
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Department of Engineering Science, Oxford University, Oxford, UK
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Lovedeep S Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Andreas Coppi
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX
| | - Sumukh Vasisht Shankar
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Bobak J Mortazavi
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
| | - Deepak L Bhatt
- Mount Sinai Fuster Heart Hospital, Icahn School of Medicine at Mount Sinai, New York, NY
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT
| | - Girish N Nadkarni
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- The Division of Data Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Akhil Vaid
- The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
- The Division of Data Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT
| |
Collapse
|
12
|
Thangaraj PM, Shankar SV, Oikonomou EK, Khera R. RCT-Twin-GAN Generates Digital Twins of Randomized Control Trials Adapted to Real-world Patients to Enhance their Inference and Application. medRxiv 2023:2023.12.06.23299464. [PMID: 38106089 PMCID: PMC10723568 DOI: 10.1101/2023.12.06.23299464] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/19/2023]
Abstract
Background Randomized clinical trials (RCTs) are designed to produce evidence in selected populations. Assessing their effects in the real-world is essential to change medical practice, however, key populations are historically underrepresented in the RCTs. We define an approach to simulate RCT-based effects in real-world settings using RCT digital twins reflecting the covariate patterns in an electronic health record (EHR). Methods We developed a Generative Adversarial Network (GAN) model, RCT-Twin-GAN, which generates a digital twin of an RCT (RCT-Twin) conditioned on covariate distributions from an EHR cohort. We improved upon a traditional tabular conditional GAN, CTGAN, with a loss function adapted for data distributions and by conditioning on multiple discrete and continuous covariates simultaneously. We assessed the similarity between a Heart Failure with preserved Ejection Fraction (HFpEF) RCT (TOPCAT), a Yale HFpEF EHR cohort, and RCT-Twin. We also evaluated cardiovascular event-free survival stratified by Spironolactone (treatment) use. Results By applying RCT-Twin-GAN to 3445 TOPCAT participants and conditioning on 3445 Yale EHR HFpEF patients, we generated RCT-Twin datasets between 1141-3445 patients in size, depending on covariate conditioning and model parameters. RCT-Twin randomly allocated spironolactone (S)/ placebo (P) arms like an RCT, was similar to RCT by a multi-dimensional distance metric, and balanced covariates (median absolute standardized mean difference (MASMD) 0.017, IQR 0.0034-0.030). The 5 EHR-conditioned covariates in RCT-Twin were closer to the EHR compared with the RCT (MASMD 0.008 vs 0.63, IQR 0.005-0.018 vs 0.59-1.11). RCT-Twin reproduced the overall effect size seen in TOPCAT (5-year cardiovascular composite outcome odds ratio (95% confidence interval) of 0.89 (0.75-1.06) in RCT vs 0.85 (0.69-1.04) in RCT-Twin). Conclusions RCT-Twin-GAN simulates RCT-derived effects in real-world patients by translating these effects to the covariate distributions of EHR patients. This key methodological advance may enable the direct translation of RCT-derived effects into real-world patient populations and may enable causal inference in real-world settings.
Collapse
Affiliation(s)
- Phyllis M Thangaraj
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Sumukh Vasisht Shankar
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
| |
Collapse
|
13
|
Oikonomou EK, Thangaraj PM, Bhatt DL, Ross JS, Young LH, Krumholz HM, Suchard MA, Khera R. An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized clinical trials. NPJ Digit Med 2023; 6:217. [PMID: 38001154 PMCID: PMC10673945 DOI: 10.1038/s41746-023-00963-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2023] [Accepted: 11/05/2023] [Indexed: 11/26/2023] Open
Abstract
Randomized clinical trials (RCT) represent the cornerstone of evidence-based medicine but are resource-intensive. We propose and evaluate a machine learning (ML) strategy of adaptive predictive enrichment through computational trial phenomaps to optimize RCT enrollment. In simulated group sequential analyses of two large cardiovascular outcomes RCTs of (1) a therapeutic drug (pioglitazone versus placebo; Insulin Resistance Intervention after Stroke (IRIS) trial), and (2) a disease management strategy (intensive versus standard systolic blood pressure reduction in the Systolic Blood Pressure Intervention Trial (SPRINT)), we constructed dynamic phenotypic representations to infer response profiles during interim analyses and examined their association with study outcomes. Across three interim timepoints, our strategy learned dynamic phenotypic signatures predictive of individualized cardiovascular benefit. By conditioning a prospective candidate's probability of enrollment on their predicted benefit, we estimate that our approach would have enabled a reduction in the final trial size across ten simulations (IRIS: -14.8% ± 3.1%, pone-sample t-test = 0.001; SPRINT: -17.6% ± 3.6%, pone-sample t-test < 0.001), while preserving the original average treatment effect (IRIS: hazard ratio of 0.73 ± 0.01 for pioglitazone vs placebo, vs 0.76 in the original trial; SPRINT: hazard ratio of 0.72 ± 0.01 for intensive vs standard systolic blood pressure, vs 0.75 in the original trial; all simulations with Cox regression-derived p value of < 0.01 for the effect of the intervention on the respective primary outcome). This adaptive framework has the potential to maximize RCT enrollment efficiency.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Phyllis M Thangaraj
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Deepak L Bhatt
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai Health System, New York, NY, USA
| | - Joseph S Ross
- Section of General Internal Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT, USA
| | - Lawrence H Young
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT, USA
| | - Marc A Suchard
- Departments of Computational Medicine and Human Genetics, David Geffen School of Medicine at UCLA, University of California, Los Angeles, CA, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA.
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA.
- Section of Biomedical Informatics and Data Science, Yale School of Public Health, New Haven, CT, USA.
| |
Collapse
|
14
|
Holste G, Oikonomou EK, Mortazavi BJ, Coppi A, Faridi KF, Miller EJ, Forrest JK, McNamara RL, Ohno-Machado L, Yuan N, Gupta A, Ouyang D, Krumholz HM, Wang Z, Khera R. Severe aortic stenosis detection by deep learning applied to echocardiography. Eur Heart J 2023; 44:4592-4604. [PMID: 37611002 PMCID: PMC11004929 DOI: 10.1093/eurheartj/ehad456] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2022] [Revised: 06/21/2023] [Accepted: 07/11/2023] [Indexed: 08/25/2023] Open
Abstract
BACKGROUND AND AIMS Early diagnosis of aortic stenosis (AS) is critical to prevent morbidity and mortality but requires skilled examination with Doppler imaging. This study reports the development and validation of a novel deep learning model that relies on two-dimensional (2D) parasternal long axis videos from transthoracic echocardiography without Doppler imaging to identify severe AS, suitable for point-of-care ultrasonography. METHODS AND RESULTS In a training set of 5257 studies (17 570 videos) from 2016 to 2020 [Yale-New Haven Hospital (YNHH), Connecticut], an ensemble of three-dimensional convolutional neural networks was developed to detect severe AS, leveraging self-supervised contrastive pretraining for label-efficient model development. This deep learning model was validated in a temporally distinct set of 2040 consecutive studies from 2021 from YNHH as well as two geographically distinct cohorts of 4226 and 3072 studies, from California and other hospitals in New England, respectively. The deep learning model achieved an area under the receiver operating characteristic curve (AUROC) of 0.978 (95% CI: 0.966, 0.988) for detecting severe AS in the temporally distinct test set, maintaining its diagnostic performance in geographically distinct cohorts [0.952 AUROC (95% CI: 0.941, 0.963) in California and 0.942 AUROC (95% CI: 0.909, 0.966) in New England]. The model was interpretable with saliency maps identifying the aortic valve, mitral annulus, and left atrium as the predictive regions. Among non-severe AS cases, predicted probabilities were associated with worse quantitative metrics of AS suggesting an association with various stages of AS severity. CONCLUSION This study developed and externally validated an automated approach for severe AS detection using single-view 2D echocardiography, with potential utility for point-of-care screening.
Collapse
Affiliation(s)
- Gregory Holste
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Bobak J Mortazavi
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, 195 Church St 5th Floor, New Haven, CT, USA
| | - Andreas Coppi
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, 195 Church St 5th Floor, New Haven, CT, USA
| | - Kamil F Faridi
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Edward J Miller
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - John K Forrest
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Robert L McNamara
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Lucila Ohno-Machado
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA
| | - Neal Yuan
- Department of Medicine, University of California San Francisco, San Francisco, CA, USA
- Division of Cardiology, San Francisco Veterans Affairs Medical Center, San Francisco, CA, USA
| | - Aakriti Gupta
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - David Ouyang
- Department of Cardiology, Smidt Heart Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA
- Division of Artificial Intelligence in Medicine, Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, 195 Church St 5th Floor, New Haven, CT, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT, USA
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, 195 Church St 5th Floor, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, 60 College St, New Haven, CT, USA
| |
Collapse
|
15
|
Oikonomou EK, Thangaraj PM, Bhatt DL, Ross JS, Young LH, Krumholz HM, Suchard MA, Khera R. An explainable machine learning-based phenomapping strategy for adaptive predictive enrichment in randomized controlled trials. medRxiv 2023:2023.06.18.23291542. [PMID: 37961715 PMCID: PMC10635225 DOI: 10.1101/2023.06.18.23291542] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/15/2023]
Abstract
Randomized controlled trials (RCT) represent the cornerstone of evidence-based medicine but are resource-intensive. We propose and evaluate a machine learning (ML) strategy of adaptive predictive enrichment through computational trial phenomaps to optimize RCT enrollment. In simulated group sequential analyses of two large cardiovascular outcomes RCTs of (1) a therapeutic drug (pioglitazone versus placebo; Insulin Resistance Intervention after Stroke (IRIS) trial), and (2) a disease management strategy (intensive versus standard systolic blood pressure reduction in the Systolic Blood Pressure Intervention Trial (SPRINT)), we constructed dynamic phenotypic representations to infer response profiles during interim analyses and examined their association with study outcomes. Across three interim timepoints, our strategy learned dynamic phenotypic signatures predictive of individualized cardiovascular benefit. By conditioning a prospective candidate's probability of enrollment on their predicted benefit, we estimate that our approach would have enabled a reduction in the final trial size across ten simulations (IRIS: -14.8% ± 3.1%, pone-sample t-test=0.001; SPRINT: -17.6% ± 3.6%, pone-sample t-test<0.001), while preserving the original average treatment effect (IRIS: hazard ratio of 0.73 ± 0.01 for pioglitazone vs placebo, vs 0.76 in the original trial; SPRINT: hazard ratio of 0.72 ± 0.01 for intensive vs standard systolic blood pressure, vs 0.75 in the original trial; all with pone-sample t-test<0.01). This adaptive framework has the potential to maximize RCT enrollment efficiency.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Phyllis M. Thangaraj
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Deepak L Bhatt
- Mount Sinai Heart, Icahn School of Medicine at Mount Sinai Health System, New York, NY, USA
| | - Joseph S Ross
- Section of General Internal Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Lawrence H Young
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Marc A Suchard
- Departments of Computational Medicine and Human Genetics, David Geffen School of Medicine at UCLA, University of California, Los Angeles, CA, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
- Section of Biomedical Informatics and Data Science, Yale School of Public Health, New Haven, CT
| |
Collapse
|
16
|
Shankar SV, Oikonomou EK, Khera R. CarDS-Plus ECG Platform: Development and Feasibility Evaluation of a Multiplatform Artificial Intelligence Toolkit for Portable and Wearable Device Electrocardiograms. medRxiv 2023:2023.10.02.23296404. [PMID: 37873174 PMCID: PMC10593062 DOI: 10.1101/2023.10.02.23296404] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/25/2023]
Abstract
In the rapidly evolving landscape of modern healthcare, the integration of wearable and portable technology provides a unique opportunity for personalized health monitoring in the community. Devices like the Apple Watch, FitBit, and AliveCor KardiaMobile have revolutionized the acquisition and processing of intricate health data streams that were previously accessible only through devices only available to healthcare providers. Amidst the variety of data collected by these gadgets, single-lead electrocardiogram (ECG) recordings have emerged as a crucial source of information for monitoring cardiovascular health. Notably, there has been significant advances in artificial intelligence capable of interpreting these 1-lead ECGs, facilitating clinical diagnosis as well as the detection of rare cardiac disorders. This design study describes the development of an innovative multi-platform system aimed at the rapid deployment of AI-based ECG solutions for clinical investigation and care delivery. The study examines various design considerations, aligning them with specific applications, and develops data flows to maximize efficiency for research and clinical use. This process encompasses the reception of single-lead ECGs from diverse wearable devices, channeling this data into a centralized data lake, and facilitating real-time inference through AI models for ECG interpretation. An evaluation of the platform demonstrates a mean duration from acquisition to reporting of results of 33.0 to 35.7 seconds, after a standard 30 second acquisition, allowing the complete process to be completed in 63.0 to 65.7 seconds. There were no substantial differences in acquisition to reporting across two commercially available devices (Apple Watch and KardiaMobile). These results demonstrate the succcessful translation of design principles into a fully integrated and efficient strategy for leveraging 1-lead ECGs across platforms and interpretation by AI-ECG algorithms. Such a platform is critical to translating AI discoveries for wearable and portable ECG devices to clinical impact through rapid deployment.
Collapse
Affiliation(s)
- Sumukh Vasisht Shankar
- Cardiovascular Data Science (CarDS) Lab, Yale School of Medicine, New Haven, CT
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Evangelos K Oikonomou
- Cardiovascular Data Science (CarDS) Lab, Yale School of Medicine, New Haven, CT
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Rohan Khera
- Cardiovascular Data Science (CarDS) Lab, Yale School of Medicine, New Haven, CT
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
| |
Collapse
|
17
|
Abstract
Artificial intelligence and machine learning are driving a paradigm shift in medicine, promising data-driven, personalized solutions for managing diabetes and the excess cardiovascular risk it poses. In this comprehensive review of machine learning applications in the care of patients with diabetes at increased cardiovascular risk, we offer a broad overview of various data-driven methods and how they may be leveraged in developing predictive models for personalized care. We review existing as well as expected artificial intelligence solutions in the context of diagnosis, prognostication, phenotyping, and treatment of diabetes and its cardiovascular complications. In addition to discussing the key properties of such models that enable their successful application in complex risk prediction, we define challenges that arise from their misuse and the role of methodological standards in overcoming these limitations. We also identify key issues in equity and bias mitigation in healthcare and discuss how the current regulatory framework should ensure the efficacy and safety of medical artificial intelligence products in transforming cardiovascular care and outcomes in diabetes.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA.
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA.
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, 195 Church St, 6th floor, New Haven, CT, 06510, USA.
| |
Collapse
|
18
|
Aminorroaya A, Dhingra LS, Oikonomou EK, Saadatagah S, Thangaraj P, Shankar SV, Spatz ES, Khera R. Development and Multinational Validation of a Novel Algorithmic Strategy for High Lp(a) Screening. medRxiv 2023:2023.09.18.23295745. [PMID: 37790355 PMCID: PMC10543220 DOI: 10.1101/2023.09.18.23295745] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/05/2023]
Abstract
Importance Elevated lipoprotein(a) [Lp(a)] is associated with atherosclerotic cardiovascular disease (ASCVD) and major adverse cardiovascular events (MACE). However, fewer than 0.5% of patients undergo Lp(a) testing, limiting the evaluation and use of novel targeted therapeutics currently under development. Objective We developed and validated a machine learning model to enable targeted screening for elevated Lp(a). Design Cross-sectional. Setting 4 multinational population-based cohorts. Participants We included 456,815 participants from the UK Biobank (UKB), the largest cohort with protocolized Lp(a) testing for model development. The model's external validity was assessed in Atherosclerosis Risk in Communities (ARIC) (N=14,484), Coronary Artery Risk Development in Young Adults (CARDIA) (N=4,124), and Multi-Ethnic Study of Atherosclerosis (MESA) (N=4,672) cohorts. Exposures Demographics, medications, diagnoses, procedures, vitals, and laboratory measurements from UKB and linked electronic health records (EHR) were candidate input features to predict high Lp(a). We used the pooled cohort equations (PCE), an ASCVD risk marker, as a comparator to identify elevated Lp(a). Main Outcomes and Measures The main outcome was elevated Lp(a) (≥150 nmol/L), and the number-needed-to-test (NNT) to find one case with elevated Lp(a). We explored the association of the model's prediction probabilities with all-cause and cardiovascular mortality, and MACE. Results The Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE) used low-density lipoprotein cholesterol, statin use, triglycerides, high-density lipoprotein cholesterol, history of ASCVD, and anti-hypertensive medication use as input features. ARISE outperformed cardiovascular risk stratification through PCE for predicting elevated Lp(a) with a significantly lower NNT (4.0 versus 8.0 [with or without PCE], P<0.001). ARISE performed comparably across external validation cohorts and subgroups, reducing the NNT by up to 67.3%, depending on the probability threshold. Over a median follow-up of 4.2 years, a high ARISE probability was also associated with a greater hazard of all-cause death and MACE (age/sex-adjusted hazard ratio [aHR], 1.35, and 1.38, respectively, P<0.001), with a greater increase in cardiovascular mortality (aHR, 2.17, P<0.001). Conclusions and Relevance ARISE optimizes screening for elevated Lp(a) using commonly available clinical features. ARISE can be deployed in EHR and other settings to encourage greater Lp(a) testing and to improve identifying cases eligible for novel targeted therapeutics in trials. KEY POINTS Question: How can we optimize the identification of individuals with elevated lipoprotein(a) [Lp(a)] who may be eligible for novel targeted therapeutics?Findings: Using 4 multinational population-based cohorts, we developed and validated a machine learning model, Algorithmic Risk Inspection for Screening Elevated Lp(a) (ARISE), to enable targeted screening for elevated Lp(a). In contrast to the pooled cohort equations that do not identify those with elevated Lp(a), ARISE reduces the "number-needed-to-test" to find one case with elevated Lp(a) by up to 67.3%.Meaning: ARISE can be deployed in electronic health records and other settings to enable greater yield of Lp(a) testing, thereby improving the identification of individuals with elevated Lp(a).
Collapse
|
19
|
Sangha V, Khunte A, Holste G, Mortazavi BJ, Wang Z, Oikonomou EK, Khera R. Biometric Contrastive Learning for Data-Efficient Deep Learning from Electrocardiographic Images. medRxiv 2023:2023.09.13.23295494. [PMID: 37745527 PMCID: PMC10516080 DOI: 10.1101/2023.09.13.23295494] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 09/26/2023]
Abstract
Objective Artificial intelligence (AI) detects heart disease from images of electrocardiograms (ECGs), however traditional supervised learning is limited by the need for large amounts of labeled data. We report the development of Biometric Contrastive Learning (BCL), a self-supervised pretraining approach for label-efficient deep learning on ECG images. Materials and Methods Using pairs of ECGs from 78,288 individuals from Yale (2000-2015), we trained a convolutional neural network to identify temporally-separated ECG pairs that varied in layouts from the same patient. We fine-tuned BCL-pretrained models to detect atrial fibrillation (AF), gender, and LVEF<40%, using ECGs from 2015-2021. We externally tested the models in cohorts from Germany and the US. We compared BCL with random initialization and general-purpose self-supervised contrastive learning for images (simCLR). Results While with 100% labeled training data, BCL performed similarly to other approaches for detecting AF/Gender/LVEF<40% with AUROC of 0.98/0.90/0.90 in the held-out test sets, it consistently outperformed other methods with smaller proportions of labeled data, reaching equivalent performance at 50% of data. With 0.1% data, BCL achieved AUROC of 0.88/0.79/0.75, compared with 0.51/0.52/0.60 (random) and 0.61/0.53/0.49 (simCLR). In external validation, BCL outperformed other methods even at 100% labeled training data, with AUROC of 0.88/0.88 for Gender and LVEF<40% compared with 0.83/0.83 (random) and 0.84/0.83 (simCLR). Discussion and Conclusion A pretraining strategy that leverages biometric signatures of different ECGs from the same patient enhances the efficiency of developing AI models for ECG images. This represents a major advance in detecting disorders from ECG images with limited labeled data.
Collapse
Affiliation(s)
- Veer Sangha
- Department of Engineering Science, Oxford University, Oxford, UK
| | - Akshay Khunte
- Department of Computer Science, Yale University, New Haven, CT, USA
| | - Gregory Holste
- Department of Electrical and Computer Engineering, The University of Texas at Austin, TX, USA
| | - Bobak J Mortazavi
- Department of Computer Science & Engineering, Texas A&M University, TX, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
| | - Zhangyang Wang
- Department of Electrical and Computer Engineering, The University of Texas at Austin, TX, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University, New Haven, CT, USA
| | - Rohan Khera
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, CT, USA
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University, New Haven, CT, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA
| |
Collapse
|
20
|
Abstract
BACKGROUND Smartphone-based health applications are increasingly popular, but their real-world use for cardiovascular risk management remains poorly understood. OBJECTIVES The purpose of this study was to investigate the patterns of tracking health goals using smart devices, including smartphones and/or tablets, in the United States. METHODS Using the nationally representative Health Information National Trends Survey for 2017 to 2020, we examined self-reported tracking of health-related goals (optimizing body weight, increasing physical activity, and/or quitting smoking) using smart devices among those with cardiovascular disease (CVD) or cardiovascular risk factors of hypertension, diabetes, obesity, and/or smoking. Survey analyses were used to obtain national estimates of use patterns and identify features associated with the use of these devices for tracking health goals. RESULTS Of 16,092 Health Information National Trends Survey participants, 10,660 had CVD or cardiovascular risk factors, representing 154.2 million (95% CI: 149.2-159.3 million) U.S. adults. Among the general U.S. adult population, 46% (95% CI: 44%-47%) tracked their health goals using their smart devices, compared with 42% (95% CI: 40%-43%) of those with or at risk of CVD. Younger age, female, Black race, higher educational attainment, and greater income were independently associated with tracking of health goals using smart devices. CONCLUSIONS Two in 5 U.S. adults with or at risk of CVD use their smart devices to track health goals. While representing a potential avenue to improve care, the lower use of smart devices among older and low-income individuals, who are at higher risk of adverse cardiovascular outcomes, requires that digital health interventions are designed so as not to exacerbate existing disparities.
Collapse
Affiliation(s)
- Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Lovedeep S. Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Arash A. Nargesi
- Heart and Vascular Center, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts, USA
| | - Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, Connecticut, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, Connecticut, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut, USA
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, Connecticut, USA
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut, USA
| |
Collapse
|
21
|
Khunte A, Sangha V, Oikonomou EK, Dhingra LS, Aminorroaya A, Mortazavi BJ, Coppi A, Brandt CA, Krumholz HM, Khera R. Detection of left ventricular systolic dysfunction from single-lead electrocardiography adapted for portable and wearable devices. NPJ Digit Med 2023; 6:124. [PMID: 37433874 PMCID: PMC10336107 DOI: 10.1038/s41746-023-00869-w] [Citation(s) in RCA: 11] [Impact Index Per Article: 11.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/06/2023] [Accepted: 06/26/2023] [Indexed: 07/13/2023] Open
Abstract
Artificial intelligence (AI) can detect left ventricular systolic dysfunction (LVSD) from electrocardiograms (ECGs). Wearable devices could allow for broad AI-based screening but frequently obtain noisy ECGs. We report a novel strategy that automates the detection of hidden cardiovascular diseases, such as LVSD, adapted for noisy single-lead ECGs obtained on wearable and portable devices. We use 385,601 ECGs for development of a standard and noise-adapted model. For the noise-adapted model, ECGs are augmented during training with random gaussian noise within four distinct frequency ranges, each emulating real-world noise sources. Both models perform comparably on standard ECGs with an AUROC of 0.90. The noise-adapted model performs significantly better on the same test set augmented with four distinct real-world noise recordings at multiple signal-to-noise ratios (SNRs), including noise isolated from a portable device ECG. The standard and noise-adapted models have an AUROC of 0.72 and 0.87, respectively, when evaluated on ECGs augmented with portable ECG device noise at an SNR of 0.5. This approach represents a novel strategy for the development of wearable-adapted tools from clinical ECG repositories.
Collapse
Affiliation(s)
- Akshay Khunte
- Department of Computer Science, Yale University, New Haven, CT, USA
| | - Veer Sangha
- Department of Computer Science, Yale University, New Haven, CT, USA
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Lovedeep S Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Bobak J Mortazavi
- Department of Computer Science & Engineering, Texas A&M University, College Station, TX, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Andreas Coppi
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Cynthia A Brandt
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA
- VA Connecticut Healthcare System, West Haven, CT, USA
| | - Harlan M Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
- Department of Health Policy and Management, Yale School of Public Health, New Haven, CT, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA.
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA.
- Section of Biomedical Informatics and Data Science, Yale School of Medicine, New Haven, CT, USA.
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA.
| |
Collapse
|
22
|
Nargesi AA, Clark C, Aminorroaya A, Chen L, Liu M, Reddy A, Amodeo S, Oikonomou EK, Suchard MA, McGuire DK, Lin Z, Inzucchi S, Khera R. Persistence on Novel Cardioprotective Antihyperglycemic Therapies in the United States. Am J Cardiol 2023; 196:89-98. [PMID: 37012183 PMCID: PMC11007258 DOI: 10.1016/j.amjcard.2023.03.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/16/2022] [Revised: 02/09/2023] [Accepted: 03/01/2023] [Indexed: 04/05/2023]
Abstract
Selected glucagon-like peptide-1 receptor agonists (GLP-1RAs) and sodium-glucose cotransporter-2 inhibitors (SGLT-2is) have cardioprotective effects in patients with type 2 diabetes mellitus (T2D) and elevated cardiovascular risk. Prescription and consistent use of these medications are essential to realizing their benefits. In a nationwide deidentified United States administrative claims database of adults with T2D, the prescription practices of GLP-1RAs and SGLT-2i were evaluated across guideline-directed co-morbidity indications from 2018 to 2020. The monthly fill rates were assessed for 12 months after the initiation of therapy by calculating the proportion of days with consistent medication use. Of 587,657 subjects with T2D, 80,196 (13.6%) were prescribed GLP-1RAs and 68,149 (11.5%) SGLT-2i from 2018 to 2020, representing 12.9% and 11.6% of patients with indications for each medication, respectively. In new initiators, 1-year fill rate was 52.5% for GLP-1RAs and 52.9% for SGLT-2i, which was higher for patients with commercial insurance than those with Medicare Advantage plans for both GLP-1RAs (59.3% vs 51.0%, p <0.001) and SGLT-2i (63.4% vs 50.3%, p <0.001). After adjusting for co-morbidities, there were higher rates of prescription fills for patients with commercial insurance (odds ratio 1.17, 95% confidence interval 1.06 to 1.29 for GLP-1RAs, and 1.59 [1.42 to 1.77] for SGLT-2i); and higher income (odds ratio 1.09 [1.06 to 1.12] for GLP-1RAs, and 1.06 [1.03 to 1.1] for SGLT-2i). From 2018 to 2020, the use of GLP-1RAs and SGLT-2i remained limited to fewer than 1 in 8 patients with T2D and indications, with 1-year fill rates around 50%. The low and inconsistent use of these medications compromises their longitudinal health outcome benefits in a period of expanding indications for their use.
Collapse
Affiliation(s)
- Arash A Nargesi
- Heart and Vascular Center, Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts
| | | | | | - Lian Chen
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, Connecticut
| | - Mengni Liu
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, Connecticut
| | | | | | | | - Marc A Suchard
- Department of Biostatistics, Fielding School of Public Health and; Department of Biomathematics, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles, California
| | - Darren K McGuire
- Division of Cardiology, Department of Internal Medicine, University of Texas Southwestern Medical Center, Dallas, Texas; Cardiology Department, Parkland Health and Hospital Systems, Dallas, Texas
| | - Zhenqiu Lin
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, Connecticut
| | - Silvio Inzucchi
- Endocrinology, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Rohan Khera
- Cardiovascular Medicine, and; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, Connecticut.
| |
Collapse
|
23
|
Dhingra LS, Aminorroaya A, Oikonomou EK, Nargesi AA, Wilson FP, Krumholz HM, Khera R. Use of Wearable Devices in Individuals With or at Risk for Cardiovascular Disease in the US, 2019 to 2020. JAMA Netw Open 2023; 6:e2316634. [PMID: 37285157 PMCID: PMC10248745 DOI: 10.1001/jamanetworkopen.2023.16634] [Citation(s) in RCA: 7] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/17/2023] [Accepted: 04/16/2023] [Indexed: 06/08/2023] Open
Abstract
Importance Wearable devices may be able to improve cardiovascular health, but the current adoption of these devices could be skewed in ways that could exacerbate disparities. Objective To assess sociodemographic patterns of use of wearable devices among adults with or at risk for cardiovascular disease (CVD) in the US population in 2019 to 2020. Design, Setting, and Participants This population-based cross-sectional study included a nationally representative sample of the US adults from the Health Information National Trends Survey (HINTS). Data were analyzed from June 1 to November 15, 2022. Exposures Self-reported CVD (history of heart attack, angina, or congestive heart failure) and CVD risk factors (≥1 risk factor among hypertension, diabetes, obesity, or cigarette smoking). Main Outcomes and Measures Self-reported access to wearable devices, frequency of use, and willingness to share health data with clinicians (referred to as health care providers in the survey). Results Of the overall 9303 HINTS participants representing 247.3 million US adults (mean [SD] age, 48.8 [17.9] years; 51% [95% CI, 49%-53%] women), 933 (10.0%) representing 20.3 million US adults had CVD (mean [SD] age, 62.2 [17.0] years; 43% [95% CI, 37%-49%] women), and 5185 (55.7%) representing 134.9 million US adults were at risk for CVD (mean [SD] age, 51.4 [16.9] years; 43% [95% CI, 37%-49%] women). In nationally weighted assessments, an estimated 3.6 million US adults with CVD (18% [95% CI, 14%-23%]) and 34.5 million at risk for CVD (26% [95% CI, 24%-28%]) used wearable devices compared with an estimated 29% (95% CI, 27%-30%) of the overall US adult population. After accounting for differences in demographic characteristics, cardiovascular risk factor profile, and socioeconomic features, older age (odds ratio [OR], 0.35 [95% CI, 0.26-0.48]), lower educational attainment (OR, 0.35 [95% CI, 0.24-0.52]), and lower household income (OR, 0.42 [95% CI, 0.29-0.60]) were independently associated with lower use of wearable devices in US adults at risk for CVD. Among wearable device users, a smaller proportion of adults with CVD reported using wearable devices every day (38% [95% CI, 26%-50%]) compared with overall (49% [95% CI, 45%-53%]) and at-risk (48% [95% CI, 43%-53%]) populations. Among wearable device users, an estimated 83% (95% CI, 70%-92%) of US adults with CVD and 81% (95% CI, 76%-85%) at risk for CVD favored sharing wearable device data with their clinicians to improve care. Conclusions and Relevance Among individuals with or at risk for CVD, fewer than 1 in 4 use wearable devices, with only half of those reporting consistent daily use. As wearable devices emerge as tools that can improve cardiovascular health, the current use patterns could exacerbate disparities unless there are strategies to ensure equitable adoption.
Collapse
Affiliation(s)
- Lovedeep S. Dhingra
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Arya Aminorroaya
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Arash Aghajani Nargesi
- Heart and Vascular Center, Brigham and Women’s Hospital, Harvard Medical School, Boston, Massachusetts
| | - Francis Perry Wilson
- Clinical and Translational Research Accelerator, Department of Medicine, Yale School of Medicine, New Haven, Connecticut
| | - Harlan M. Krumholz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, Connecticut
- Department of Health Policy and Management, Yale School of Public Health, New Haven, Connecticut
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, Connecticut
- Center for Outcomes Research and Evaluation (CORE), Yale New Haven Hospital, New Haven, Connecticut
- Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, Connecticut
| |
Collapse
|
24
|
Khunte A, Sangha V, Dhingra L, Oikonomou EK, Mortazavi B, Khera R. DEEP LEARNING-BASED DETECTION OF LEFT VENTRICULAR SYSTOLIC DYSFUNCTION FROM NOISY SINGLE LEAD ELECTROCARDIOGRAPHY ADAPTED FOR WEARABLE DEVICES. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)02706-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
25
|
Pires J, Oikonomou EK, Agarwal R, Liu YH, miller EJ, Sinusas AJ, Feher A. IN PATIENTS UNDERGOING NUCLEAR MYOCARDIAL PERFUSION IMAGING, RHEUMATOID ARTHRITIS IS ASSOCIATED WITH INCREASED RISK OF ADVERSE CARDIOVASCULAR EVENTS INDEPENDENT OF MYOCARDIAL ISCHEMIA. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)01911-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
26
|
Oikonomou EK, Spatz ES, Ross JS, Suchard M, Krumholz HM, Khera R. A MACHINE LEARNING-GUIDED APPROACH FOR ADAPTIVE TRIAL ENRICHMENT AND ACCELERATION OF CARDIOVASCULAR OUTCOME TRIALS: INSIGHTS FROM THE SPRINT AND ACCORD-BP TRIALS. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)02758-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/07/2023]
|
27
|
Sangha V, Khunte A, Holste G, Mortazavi B, Wang Z, Oikonomou EK, Khera R. BIOMETRIC CONTRASTIVE MODELING FOR DATA-EFFICIENT DEEP LEARNING FROM ELECTROCARDIOGRAPHIC IMAGES. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)02847-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/07/2023]
|
28
|
Oikonomou EK, Suchard M, Miller EJ, Velazquez EJ, Khera R. MECHANISTIC EVALUATION OF AN AI-DRIVEN CLINICAL DECISION SUPPORT TOOL TO PERSONALIZE THE USE OF ANATOMICAL TESTING IN SUSPECTED CORONARY ARTERY DISEASE. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)01804-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
29
|
Sangha V, Oikonomou EK, Khunte A, Gupta K, Mortazavi B, Khera R. SMART-AS: A NOVEL ARTIFICIAL INTELLIGENCE TOOL TO DETECT SEVERE AORTIC STENOSIS FROM ELECTROCARDIOGRAPHIC IMAGES. J Am Coll Cardiol 2023. [DOI: 10.1016/s0735-1097(23)02853-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/06/2023]
|
30
|
MCCLOSKEY V, Nasir K, Khera R, Oikonomou EK, Diaz R, Kenney R, Aguilar R, Gulati M, Cingolani OH, Gluckman TJ, Blankstein R, Hernandez MB, Rivera J. Abstract 60: Impact of a Multisite, Protocol-Driven, Nurse Practitioner-Led, Cardiovascular Prevention Program in a Hispanic Medicare Advantage Population at High Risk for ASCVD: Healthy Heart Program at Cano Health. Circulation 2023. [DOI: 10.1161/circ.147.suppl_1.60] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 03/16/2023]
Abstract
Introduction:
Despite availability of effective and inexpensive pharmacologic therapies for hypercholesterolemia and hypertension, many patients at high risk for atherosclerotic cardiovascular disease (ASCVD) do not achieve optimal low-density lipoprotein (LDL) and systolic blood pressure (SBP) levels. We hypothesized that risk factor control could be improved by using nurse practitioners and a guideline-directed protocol in a Medicare Advantage (MA) population.
Methods:
We designed and implemented an ongoing 18 site, multistate (FL, TX, NV), ASCVD risk assessment and management program (Healthy Heart) in a large national MA primary care clinic (Cano Health). The cardiometabolic risk assessment and management program was designed by a team of preventive cardiologists, with the plan of being Nurse Practitioner (NP)-led, with remote support by a cardiologist. Protocols provided details on initiation and titration of drug therapy to achieve LDL-C and SBP goals. Patients with organ transplants, advanced cancer, an ejection fraction <35%, and on hemodialysis were excluded.
Results:
From October 2021-October 2022, 5430 patients were enrolled in the program. A total of 1858 (34.2%) had established ASCVD, 1033 (19.0%) had diabetes mellitus (DM). A total of 713 (13.1%) had both ASCVD and DM. In patients who had ASCVD and diabetes together, high intensity statin use increased from 39.4% to 68.3% after enrollment; 52.66% achieved an LDL-C <70 mg/dl after enrollment compared to 31.0% at baseline. Antihypertensive medications were intensified in 408/1041 (39.2%) of ASCVD and 276/558 (49.5%) of DM patients, with a higher proportion achieving a SBP <130 mm Hg after enrollment.
Conclusions:
Implementing a novel cardiovascular prevention program in a population of mostly Hispanic MA patients at high risk for ASCVD, using NPs, with strict adherence to a step-by-step evidence-based protocol supervised by cardiologists, is associated with reduction in LDL levels and SBP and with improvement in reaching LDL and SBP targets.
Collapse
|
31
|
Oikonomou EK, Spatz ES, Suchard MA, Khera R. Individualising intensive systolic blood pressure reduction in hypertension using computational trial phenomaps and machine learning: a post-hoc analysis of randomised clinical trials. Lancet Digit Health 2022; 4:e796-e805. [PMID: 36307193 PMCID: PMC9768739 DOI: 10.1016/s2589-7500(22)00170-4] [Citation(s) in RCA: 14] [Impact Index Per Article: 7.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2021] [Revised: 08/06/2022] [Accepted: 08/17/2022] [Indexed: 12/23/2022]
Abstract
BACKGROUND The cardiovascular benefits of intensive systolic blood pressure control vary across clinical populations tested in large randomised clinical trials. We aimed to evaluate the application of machine learning to clinical trials of patients without and with type 2 diabetes to define the personalised cardiovascular benefit of intensive control of systolic blood pressure. METHODS In SPRINT, a trial of intensive (systolic blood pressure <120 mm Hg) versus standard (systolic blood pressure <140 mm Hg) systolic blood pressure control in patients without type 2 diabetes, we defined a phenotypic representation of the study population using 59 baseline variables. We extracted personalised treatment effect estimates for the primary outcome, time-to-first major adverse cardiovascular event (MACE; cardiovascular death, myocardial infarction or acute coronary syndrome, stroke, and acute decompensated heart failure), through iterative Cox regression analyses providing average hazard ratio (HR) estimates weighted for the phenotypic distance of each participant from the index patient of each iteration. Next, we trained an extreme gradient boosting algorithm (known as XGBoost) to predict the personalised effect of intensive systolic blood pressure control using features most consistently linked to increased personalised benefit, before evaluating its performance in the ACCORD BP trial of patients with type 2 diabetes randomly assigned to receive intensive versus standard systolic blood pressure control. We stratified patients based on their predicted treatment effect, and key demographic groups (age, sex, cardiovascular disease, and smoking). We assessed the presence of heterogeneity with an interaction test, and assessed the performance of the algorithm in a simulation analysis of SPRINT in the presence or absence of an artificially introduced heterogeneous treatment effect. FINDINGS From SPRINT, we included all 9361 study participants (mean age 67·9 years [SD 9·4], 3332 [35·6%] female) who underwent randomisation to either intensive (n=4678) or standard (n=4683) treatment. The median individualised HR for MACE was 0·63 (IQR 0·53-0·78). An eight-feature tool built for this analysis to predict personalised benefit in SPRINT was externally tested in ACCORD BP (4733 participants (mean age 62·7 years [SD 6·7], 2258 [47·7%] female), wherein it successfully identified individuals with differential benefit from intensive versus standard systolic blood pressure control (adjusted HR for MACE of 0·70 [95% CI 0·55-0·90] in individuals with above-median MACE benefit versus 1·05 [95% CI 0·84-1·32] for below-median predicted benefit; pinteraction=0·0184). Subgroup analysis based on age (<65 years: HR 0·89 [95% CI 0·71-1·12]; ≥65 years: 0·85 [0·67-1·09]), sex (male: 0·89 [0·72-1·10]; female: 0·85 [0·65-1·10]), established cardiovascular disease (no: 0·89 [0·70-1·14]; yes: 0·84 [0·67-1·06]), or active smoking (no: 0·85 [0·71-1·02]; yes: 1·01 [0·64-1·60]) did not identify groups with heterogeneity of treatment effect. In a simulation analysis of SPRINT, the proposed algorithm detected groups with heterogeneous treatment effects in the presence, but not absence, of simulated subgroup differences. INTERPRETATION By use of machine learning to define an individual's personalised benefit through phenotypic representations of clinical trials, we created a practical tool for individualising the selection of intensive versus standard systolic blood pressure control in patients without and with type 2 diabetes. FUNDING National Heart, Lung, and Blood Institute of the US National Institutes of Health.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA
| | - Erica S Spatz
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA
| | - Marc A Suchard
- Department of Biostatistics, Fielding School of Public Health, University of California, Los Angeles, Los Angeles, CA, USA; Department of Computational Medicine, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles CA, USA; Department of Human Genetics, David Geffen School of Medicine at UCLA, University of California, Los Angeles, Los Angeles CA, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT, USA; Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT, USA; Section of Health Informatics, Department of Biostatistics, Yale School of Public Health, New Haven, CT, USA.
| |
Collapse
|
32
|
Kotanidis CP, Xie C, Alexander D, Rodrigues JCL, Burnham K, Mentzer A, O'Connor D, Knight J, Siddique M, Lockstone H, Thomas S, Kotronias R, Oikonomou EK, Badi I, Lyasheva M, Shirodaria C, Lumley SF, Constantinides B, Sanderson N, Rodger G, Chau KK, Lodge A, Tsakok M, Gleeson F, Adlam D, Rao P, Indrajeet D, Deshpande A, Bajaj A, Hudson BJ, Srivastava V, Farid S, Krasopoulos G, Sayeed R, Ho LP, Neubauer S, Newby DE, Channon KM, Deanfield J, Antoniades C. Constructing custom-made radiotranscriptomic signatures of vascular inflammation from routine CT angiograms: a prospective outcomes validation study in COVID-19. Lancet Digit Health 2022; 4:e705-e716. [PMID: 36038496 PMCID: PMC9417284 DOI: 10.1016/s2589-7500(22)00132-7] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/02/2022] [Revised: 06/16/2022] [Accepted: 07/05/2022] [Indexed: 12/15/2022]
Abstract
BACKGROUND Direct evaluation of vascular inflammation in patients with COVID-19 would facilitate more efficient trials of new treatments and identify patients at risk of long-term complications who might respond to treatment. We aimed to develop a novel artificial intelligence (AI)-assisted image analysis platform that quantifies cytokine-driven vascular inflammation from routine CT angiograms, and sought to validate its prognostic value in COVID-19. METHODS For this prospective outcomes validation study, we developed a radiotranscriptomic platform that uses RNA sequencing data from human internal mammary artery biopsies to develop novel radiomic signatures of vascular inflammation from CT angiography images. We then used this platform to train a radiotranscriptomic signature (C19-RS), derived from the perivascular space around the aorta and the internal mammary artery, to best describe cytokine-driven vascular inflammation. The prognostic value of C19-RS was validated externally in 435 patients (331 from study arm 3 and 104 from study arm 4) admitted to hospital with or without COVID-19, undergoing clinically indicated pulmonary CT angiography, in three UK National Health Service (NHS) trusts (Oxford, Leicester, and Bath). We evaluated the diagnostic and prognostic value of C19-RS for death in hospital due to COVID-19, did sensitivity analyses based on dexamethasone treatment, and investigated the correlation of C19-RS with systemic transcriptomic changes. FINDINGS Patients with COVID-19 had higher C19-RS than those without (adjusted odds ratio [OR] 2·97 [95% CI 1·43-6·27], p=0·0038), and those infected with the B.1.1.7 (alpha) SARS-CoV-2 variant had higher C19-RS values than those infected with the wild-type SARS-CoV-2 variant (adjusted OR 1·89 [95% CI 1·17-3·20] per SD, p=0·012). C19-RS had prognostic value for in-hospital mortality in COVID-19 in two testing cohorts (high [≥6·99] vs low [<6·99] C19-RS; hazard ratio [HR] 3·31 [95% CI 1·49-7·33], p=0·0033; and 2·58 [1·10-6·05], p=0·028), adjusted for clinical factors, biochemical biomarkers of inflammation and myocardial injury, and technical parameters. The adjusted HR for in-hospital mortality was 8·24 (95% CI 2·16-31·36, p=0·0019) in patients who received no dexamethasone treatment, but 2·27 (0·69-7·55, p=0·18) in those who received dexamethasone after the scan, suggesting that vascular inflammation might have been a therapeutic target of dexamethasone in COVID-19. Finally, C19-RS was strongly associated (r=0·61, p=0·00031) with a whole blood transcriptional module representing dysregulation of coagulation and platelet aggregation pathways. INTERPRETATION Radiotranscriptomic analysis of CT angiography scans introduces a potentially powerful new platform for the development of non-invasive imaging biomarkers. Application of this platform in routine CT pulmonary angiography scans done in patients with COVID-19 produced the radiotranscriptomic signature C19-RS, a marker of cytokine-driven inflammation driving systemic activation of coagulation and responsible for adverse clinical outcomes, which predicts in-hospital mortality and might allow targeted therapy. FUNDING Engineering and Physical Sciences Research Council, British Heart Foundation, Oxford BHF Centre of Research Excellence, Innovate UK, NIHR Oxford Biomedical Research Centre, Wellcome Trust, Onassis Foundation.
Collapse
Affiliation(s)
- Christos P Kotanidis
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Cheng Xie
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Donna Alexander
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | | | | | | | - Daniel O'Connor
- Oxford Vaccine Group, Department of Paediatrics, University of Oxford and NIHR Oxford Biomedical Research Centre, Oxford, UK
| | - Julian Knight
- MRC Human Immunology Unit, Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK
| | - Muhammad Siddique
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; Caristo Diagnostics Ltd, Oxford, UK
| | - Helen Lockstone
- Wellcome Trust Centre for Human Genetics, University of Oxford, Oxford, UK
| | - Sheena Thomas
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Rafail Kotronias
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Evangelos K Oikonomou
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; Department of Internal Medicine, Yale-New Haven Hospital, Yale School of Medicine, New Haven, CT, USA
| | - Ileana Badi
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Maria Lyasheva
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | | | - Sheila F Lumley
- Nuffield Department of Medicine, University of Oxford, Oxford, UK
| | | | | | - Gillian Rodger
- Nuffield Department of Medicine, University of Oxford, Oxford, UK
| | - Kevin K Chau
- Nuffield Department of Medicine, University of Oxford, Oxford, UK
| | - Archie Lodge
- Medical Sciences Division, University of Oxford, Oxford, UK
| | - Maria Tsakok
- Department of Radiology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - Fergus Gleeson
- Department of Radiology, John Radcliffe Hospital, Oxford University Hospitals NHS Foundation Trust, Oxford, UK
| | - David Adlam
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | - Praveen Rao
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | - Das Indrajeet
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | - Aparna Deshpande
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | - Amrita Bajaj
- Department of Cardiovascular Sciences and NIHR Leicester Biomedical Research Centre, University of Leicester, Leicester, UK
| | - Benjamin J Hudson
- Department of Radiology, Royal United Hospitals Bath NHS Foundation Trust, Bath, UK
| | | | - Shakil Farid
- Department of Cardiothoracic Surgery, Oxford, UK
| | | | - Rana Sayeed
- Department of Cardiothoracic Surgery, Oxford, UK
| | - Ling-Pei Ho
- MRC Human Immunology Unit, Weatherall Institute of Molecular Medicine, University of Oxford, Oxford, UK
| | - Stefan Neubauer
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - David E Newby
- British Heart Foundation Centre for Cardiovascular Science, University of Edinburgh, Edinburgh, UK
| | - Keith M Channon
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; British Heart Foundation-National Institute of Health Research Cardiovascular Partnership, Oxford NIHR Biomedical Research Centre, Oxford, UK
| | - John Deanfield
- Institute of Cardiovascular Sciences, University College London, London, UK
| | - Charalambos Antoniades
- Acute Multidisciplinary Imaging & Interventional Centre, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK.
| |
Collapse
|
33
|
Oikonomou EK, Suchard MA, McGuire DK, Khera R. Phenomapping-Derived Tool to Individualize the Effect of Canagliflozin on Cardiovascular Risk in Type 2 Diabetes. Diabetes Care 2022; 45:965-974. [PMID: 35120199 PMCID: PMC9016734 DOI: 10.2337/dc21-1765] [Citation(s) in RCA: 11] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/22/2021] [Accepted: 01/09/2022] [Indexed: 02/03/2023]
Abstract
OBJECTIVE Sodium-glucose cotransporter 2 (SGLT2) inhibitors have well-documented cardioprotective effects but are underused, partly because of high cost. We aimed to develop a machine learning-based decision support tool to individualize the atherosclerotic cardiovascular disease (ASCVD) benefit of canagliflozin in type 2 diabetes. RESEARCH DESIGN AND METHODS We constructed a topological representation of the Canagliflozin Cardiovascular Assessment Study (CANVAS) using 75 baseline variables collected from 4,327 patients with type 2 diabetes randomly assigned 1:1:1 to one of two canagliflozin doses (n = 2,886) or placebo (n = 1,441). Within each patient's 5% neighborhood, we calculated age- and sex-adjusted risk estimates for major adverse cardiovascular events (MACEs). An extreme gradient boosting algorithm was trained to predict the personalized ASCVD effect of canagliflozin using features most predictive of topological benefit. For validation, this algorithm was applied to the CANVAS-Renal (CANVAS-R) trial, comprising 5,808 patients with type 2 diabetes randomly assigned 1:1 to canagliflozin or placebo. RESULTS In CANVAS (mean age 60.9 ± 8.1 years; 33.9% women), 1,605 (37.1%) patients had a neighborhood hazard ratio (HR) more protective than the effect estimate of 0.86 reported for MACEs in the original trial. A 15-variable tool, INSIGHT, trained to predict the personalized ASCVD effects of canagliflozin in CANVAS, was tested in CANVAS-R (mean age 62.4 ± 8.4 years; 2,164 [37.3%] women), where it identified patient phenotypes with greater ASCVD canagliflozin effects (adjusted HR 0.60 [95% CI 0.41-0.89] vs. 0.99 [95% CI 0.76-1.29]; Pinteraction = 0.04). CONCLUSIONS We present an evidence-based, machine learning-guided algorithm to personalize the prescription of SGLT2 inhibitors for patients with type 2 diabetes for ASCVD effects.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT
| | - Marc A Suchard
- Department of Biostatistics, Fielding School of Public Health, University of California, Los Angeles, Los Angeles, CA.,Departments of Computational Medicine and Human Genetics, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA
| | - Darren K McGuire
- University of Texas Southwestern Medical Center and Parkland Health and Hospital System, Dallas, TX
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, New Haven, CT.,Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, New Haven, CT
| |
Collapse
|
34
|
Kwan JM, Oikonomou EK, Henry ML, Sinusas AJ. Multimodality Advanced Cardiovascular and Molecular Imaging for Early Detection and Monitoring of Cancer Therapy-Associated Cardiotoxicity and the Role of Artificial Intelligence and Big Data. Front Cardiovasc Med 2022; 9:829553. [PMID: 35369354 PMCID: PMC8964995 DOI: 10.3389/fcvm.2022.829553] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2021] [Accepted: 01/12/2022] [Indexed: 12/12/2022] Open
Abstract
Cancer mortality has improved due to earlier detection via screening, as well as due to novel cancer therapies such as tyrosine kinase inhibitors and immune checkpoint inhibitions. However, similarly to older cancer therapies such as anthracyclines, these therapies have also been documented to cause cardiotoxic events including cardiomyopathy, myocardial infarction, myocarditis, arrhythmia, hypertension, and thrombosis. Imaging modalities such as echocardiography and magnetic resonance imaging (MRI) are critical in monitoring and evaluating for cardiotoxicity from these treatments, as well as in providing information for the assessment of function and wall motion abnormalities. MRI also allows for additional tissue characterization using T1, T2, extracellular volume (ECV), and delayed gadolinium enhancement (DGE) assessment. Furthermore, emerging technologies may be able to assist with these efforts. Nuclear imaging using targeted radiotracers, some of which are already clinically used, may have more specificity and help provide information on the mechanisms of cardiotoxicity, including in anthracycline mediated cardiomyopathy and checkpoint inhibitor myocarditis. Hyperpolarized MRI may be used to evaluate the effects of oncologic therapy on cardiac metabolism. Lastly, artificial intelligence and big data of imaging modalities may help predict and detect early signs of cardiotoxicity and response to cardioprotective medications as well as provide insights on the added value of molecular imaging and correlations with cardiovascular outcomes. In this review, the current imaging modalities used to assess for cardiotoxicity from cancer treatments are discussed, in addition to ongoing research on targeted molecular radiotracers, hyperpolarized MRI, as well as the role of artificial intelligence (AI) and big data in imaging that would help improve the detection and prognostication of cancer-treatment cardiotoxicity.
Collapse
Affiliation(s)
- Jennifer M. Kwan
- Section of Cardiovascular Medicine, Yale University School of Medicine, New Haven, CT, United States
| | - Evangelos K. Oikonomou
- Section of Cardiovascular Medicine, Yale University School of Medicine, New Haven, CT, United States
| | - Mariana L. Henry
- Geisel School of Medicine at Dartmouth, Hanover, NH, United States
| | - Albert J. Sinusas
- Section of Cardiovascular Medicine, Yale University School of Medicine, New Haven, CT, United States
- Department of Radiology and Biomedical Imaging, Yale University School of Medicine, New Haven, CT, United States
- Department of Biomedical Engineering, Yale University, New Haven, CT, United States
| |
Collapse
|
35
|
Antonopoulos AS, Angelopoulos A, Papanikolaou P, Simantiris S, Oikonomou EK, Vamvakaris K, Koumpoura A, Farmaki M, Trivella M, Vlachopoulos C, Tsioufis K, Antoniades C, Tousoulis D. Biomarkers of Vascular Inflammation for Cardiovascular Risk Prognostication: A Meta-Analysis. JACC Cardiovasc Imaging 2022; 15:460-471. [PMID: 34801448 DOI: 10.1016/j.jcmg.2021.09.014] [Citation(s) in RCA: 26] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/12/2021] [Revised: 09/08/2021] [Accepted: 09/10/2021] [Indexed: 12/23/2022]
Abstract
OBJECTIVES The purpose of this study was to systematically explore the added value of biomarkers of vascular inflammation for cardiovascular prognostication on top of clinical risk factors. BACKGROUND Measurement of biomarkers of vascular inflammation is advocated for the risk stratification for coronary heart disease (CHD). METHODS We systematically explored published reports in MEDLINE for cohort studies on the prognostic value of common biomarkers of vascular inflammation in stable patients without known CHD. These included common circulating inflammatory biomarkers (ie, C-reactive protein, interleukin-6 and tumor necrosis factor-a, arterial positron emission tomography/computed tomography and coronary computed tomography angiography-derived biomarkers of vascular inflammation, including anatomical high-risk plaque features and perivascular fat imaging. The main endpoint was the difference in c-index (Δ[c-index]) with the use of inflammatory biomarkers for major adverse cardiovascular events (MACEs) and mortality. We calculated I2 to test heterogeneity. This study is registered with PROSPERO (CRD42020181158). RESULTS A total of 104,826 relevant studies were screened and a final of 39 independent studies (175,778 individuals) were included in the quantitative synthesis. Biomarkers of vascular inflammation provided added prognostic value for the composite endpoint and for MACEs only (pooled estimate for Δ[c-index]% 2.9, 95% CI: 1.7-4.1 and 3.1, 95% CI: 1.8-4.5, respectively). Coronary computed tomography angiography-related biomarkers were associated with the highest added prognostic value for MACEs: high-risk plaques 5.8%, 95% CI: 0.6 to 11.0, and perivascular adipose tissue (on top of coronary atherosclerosis extent and high-risk plaques): 8.2%, 95% CI: 4.0 to 12.5). In meta-regression analysis, the prognostic value of inflammatory biomarkers was independent of other confounders including study size, length of follow-up, population event incidence, the performance of the baseline model, and the level of statistical adjustment. Limitations in the published literature include the lack of reporting of other metrics of improvement of risk stratification, the net clinical benefit, or the cost-effectiveness of such biomarkers in clinical practice. CONCLUSIONS The use of biomarkers of vascular inflammation enhances risk discrimination for cardiovascular events.
Collapse
Affiliation(s)
- Alexios S Antonopoulos
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece; RDM Division of Cardiovascular Medicine, University of Oxford, United Kingdom.
| | - Andreas Angelopoulos
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Paraskevi Papanikolaou
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Spyridon Simantiris
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Evangelos K Oikonomou
- RDM Division of Cardiovascular Medicine, University of Oxford, United Kingdom; Department of Internal Medicine, Yale School of Medicine, Yale-New Haven Hospital, Connecticut, USA
| | - Konstantinos Vamvakaris
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Alkmini Koumpoura
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Maria Farmaki
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | | | - Charalambos Vlachopoulos
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | - Konstantinos Tsioufis
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| | | | - Dimitris Tousoulis
- 1(st) Cardiology Department, School of Health Sciences, National and Kapodistrian University of Athens, Greece
| |
Collapse
|
36
|
Nargesi AA, Clark C, Liu M, Chen L, Reddy A, Amodeo S, Oikonomou EK, Suchard M, Lipska K, McGuire DK, Lin Z, Inzucchi SE, Krumholz HM, Khera R. U.S. PATTERNS OF DRUG UTILIZATION AND PRESCRIPTION FILLS FOR PROVEN CARDIOPROTECTIVE ANTI-HYPERGLYCEMIC AGENTS. J Am Coll Cardiol 2022. [DOI: 10.1016/s0735-1097(22)02437-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/18/2022]
|
37
|
Oikonomou EK, Suchard M, Khera R. PERSONALIZING THE THERAPEUTIC BENEFIT FROM SPIRONOLACTONE IN HEART FAILURE WITH PRESERVED EJECTION FRACTION THROUGH COMPUTATIONAL PHENOMAPS OF THE TOPCAT TRIAL AND MACHINE LEARNING. J Am Coll Cardiol 2022. [DOI: 10.1016/s0735-1097(22)01415-2] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
|
38
|
Bellumkonda L, Oikonomou EK, Hsueh C, Maulion C, Testani J, Patel J. The Impact of Induction Therapy on Mortality and Treated Rejection in Cardiac Transplantation: A Retrospective Study. J Heart Lung Transplant 2022; 41:482-491. [DOI: 10.1016/j.healun.2022.01.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/03/2021] [Revised: 12/07/2021] [Accepted: 01/01/2022] [Indexed: 11/27/2022] Open
|
39
|
Kondo H, Akoumianakis I, Badi I, Akawi N, Kotanidis CP, Polkinghorne M, Stadiotti I, Sommariva E, Antonopoulos AS, Carena MC, Oikonomou EK, Reus EM, Sayeed R, Krasopoulos G, Srivastava V, Farid S, Chuaiphichai S, Shirodaria C, Channon KM, Casadei B, Antoniades C. Effects of canagliflozin on human myocardial redox signalling: clinical implications. Eur Heart J 2021; 42:4947-4960. [PMID: 34293101 PMCID: PMC8691807 DOI: 10.1093/eurheartj/ehab420] [Citation(s) in RCA: 46] [Impact Index Per Article: 15.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/14/2020] [Revised: 01/14/2021] [Accepted: 06/18/2021] [Indexed: 01/06/2023] Open
Abstract
AIMS Recent clinical trials indicate that sodium-glucose cotransporter 2 (SGLT2) inhibitors improve cardiovascular outcomes in heart failure patients, but the underlying mechanisms remain unknown. We explored the direct effects of canagliflozin, an SGLT2 inhibitor with mild SGLT1 inhibitory effects, on myocardial redox signalling in humans. METHODS AND RESULTS Study 1 included 364 patients undergoing cardiac surgery. Right atrial appendage biopsies were harvested to quantify superoxide (O2.-) sources and the expression of inflammation, fibrosis, and myocardial stretch genes. In Study 2, atrial tissue from 51 patients was used ex vivo to study the direct effects of canagliflozin on NADPH oxidase activity and nitric oxide synthase (NOS) uncoupling. Differentiated H9C2 and primary human cardiomyocytes (hCM) were used to further characterize the underlying mechanisms (Study 3). SGLT1 was abundantly expressed in human atrial tissue and hCM, contrary to SGLT2. Myocardial SGLT1 expression was positively associated with O2.- production and pro-fibrotic, pro-inflammatory, and wall stretch gene expression. Canagliflozin reduced NADPH oxidase activity via AMP kinase (AMPK)/Rac1signalling and improved NOS coupling via increased tetrahydrobiopterin bioavailability ex vivo and in vitro. These were attenuated by knocking down SGLT1 in hCM. Canagliflozin had striking ex vivo transcriptomic effects on myocardial redox signalling, suppressing apoptotic and inflammatory pathways in hCM. CONCLUSIONS We demonstrate for the first time that canagliflozin suppresses myocardial NADPH oxidase activity and improves NOS coupling via SGLT1/AMPK/Rac1 signalling, leading to global anti-inflammatory and anti-apoptotic effects in the human myocardium. These findings reveal a novel mechanism contributing to the beneficial cardiac effects of canagliflozin.
Collapse
Affiliation(s)
- Hidekazu Kondo
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
- Department of Cardiology and Clinical Examination, Faculty of Medicine, Oita University, 1-1 Idaigaoka, Hasama, Yufu, Oita 879-5593, Japan
| | - Ioannis Akoumianakis
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Ileana Badi
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Nadia Akawi
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
- Department of Genetics and Genomics, College of Medicine and Health Sciences, United Arab Emirates University, Khalifa Ibn Zayed Street, Al Maqam, Al-Ain, P.O. Box 17666, United Arab Emirates
| | - Christos P Kotanidis
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Murray Polkinghorne
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Ilaria Stadiotti
- Unit of Vascular Biology and Regenerative Medicine, Centro Cardiologico Monzino IRCCS, via Carlo Parea 4, 20138, Milan, Italy
| | - Elena Sommariva
- Unit of Vascular Biology and Regenerative Medicine, Centro Cardiologico Monzino IRCCS, via Carlo Parea 4, 20138, Milan, Italy
| | - Alexios S Antonopoulos
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Maria C Carena
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Evangelos K Oikonomou
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Elsa Mauricio Reus
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Rana Sayeed
- Oxford University Hospitals NHS Trust, Headley Way, Oxford OX3 9DU, UK
| | | | - Vivek Srivastava
- Oxford University Hospitals NHS Trust, Headley Way, Oxford OX3 9DU, UK
| | - Shakil Farid
- Oxford University Hospitals NHS Trust, Headley Way, Oxford OX3 9DU, UK
| | - Surawee Chuaiphichai
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Cheerag Shirodaria
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, Oxford OX2 0HP, UK
| | - Keith M Channon
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
- Oxford University Hospitals NHS Trust, Headley Way, Oxford OX3 9DU, UK
| | - Barbara Casadei
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
| | - Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, L6 West Wing, John Radcliffe Hospital, Headley Way, Oxford OX3 9DU, UK
- Oxford University Hospitals NHS Trust, Headley Way, Oxford OX3 9DU, UK
- Acute Vascular Imaging Centre, University of Oxford, Headley Way, Oxford OX3 9DU, UK
| |
Collapse
|
40
|
Oikonomou EK, Antonopoulos AS, Schottlander D, Marwan M, Mathers C, Tomlins P, Siddique M, Klüner LV, Shirodaria C, Mavrogiannis MC, Thomas S, Fava A, Deanfield J, Channon KM, Neubauer S, Desai MY, Achenbach S, Antoniades C. Standardized measurement of coronary inflammation using cardiovascular computed tomography: integration in clinical care as a prognostic medical device. Cardiovasc Res 2021; 117:2677-2690. [PMID: 34450625 DOI: 10.1093/cvr/cvab286] [Citation(s) in RCA: 12] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/07/2021] [Accepted: 08/27/2021] [Indexed: 12/12/2022] Open
Abstract
AIMS Coronary computed tomography angiography (CCTA) is a first-line modality in the investigation of suspected coronary artery disease (CAD). Mapping of perivascular fat attenuation index (FAI) on routine CCTA enables the non-invasive detection of coronary artery inflammation by quantifying spatial changes in perivascular fat composition. We now report the performance of a new medical device, CaRi-Heart®, which integrates standardized FAI mapping together with clinical risk factors and plaque metrics to provide individualized cardiovascular risk prediction. METHODS AND RESULTS The study included 3912 consecutive patients undergoing CCTA as part of clinical care in the USA (n = 2040) and Europe (n = 1872). These cohorts were used to generate age-specific nomograms and percentile curves as reference maps for the standardized interpretation of FAI. The first output of CaRi-Heart® is the FAI-Score of each coronary artery, which provides a measure of coronary inflammation adjusted for technical, biological, and anatomical characteristics. FAI-Score is then incorporated into a risk prediction algorithm together with clinical risk factors and CCTA-derived coronary plaque metrics to generate the CaRi-Heart® Risk that predicts the likelihood of a fatal cardiac event at 8 years. CaRi-Heart® Risk was trained in the US population and its performance was validated externally in the European population. It improved risk discrimination over a clinical risk factor-based model [Δ(C-statistic) of 0.085, P = 0.01 in the US Cohort and 0.149, P < 0.001 in the European cohort] and had a consistent net clinical benefit on decision curve analysis above a baseline traditional risk factor-based model across the spectrum of cardiac risk. CONCLUSION Mapping of perivascular FAI on CCTA enables the non-invasive detection of coronary artery inflammation by quantifying spatial changes in perivascular fat composition. We now report the performance of a new medical device, CaRi-Heart®, which allows standardized measurement of coronary inflammation by calculating the FAI-Score of each coronary artery. The CaRi-Heart® device provides a reliable prediction of the patient's absolute risk for a fatal cardiac event by incorporating traditional cardiovascular risk factors along with comprehensive CCTA coronary plaque and perivascular adipose tissue phenotyping. This integration advances the prognostic utility of CCTA for individual patients and paves the way for its use as a dual diagnostic and prognostic tool among patients referred for CCTA.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine, 333 Cedar St, New Haven, CT 06510, USA
| | - Alexios S Antonopoulos
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - David Schottlander
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, OX2 0HP, Oxford, UK
| | - Mohammad Marwan
- Department of Cardiology, Friedrich-Alexander-Universität Erlangen-Nürnberg, Maximilianspl 2, 91054 Erlangen, Germany
| | - Chris Mathers
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, OX2 0HP, Oxford, UK
| | - Pete Tomlins
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, OX2 0HP, Oxford, UK
| | - Muhammad Siddique
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, OX2 0HP, Oxford, UK
| | - Laura V Klüner
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - Cheerag Shirodaria
- Caristo Diagnostics, 1st Floor, New Barclay House, 234 Botley Rd, OX2 0HP, Oxford, UK
| | - Michail C Mavrogiannis
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - Sheena Thomas
- Acute Vascular Imaging Centre, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - Agostina Fava
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Cleveland, OH44195, USA
| | - John Deanfield
- Institute of Cardiovascular Science, Faculty of Population Health Sciences, University College London, Gower Street, London WC1E 6BTUK
| | - Keith M Channon
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- British Heart Foundation Centre of Research Excellence, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- National Institute of Health Research (NIHR), Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - Stefan Neubauer
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- British Heart Foundation Centre of Research Excellence, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- National Institute of Health Research (NIHR), Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| | - Milind Y Desai
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Cleveland, OH44195, USA
| | - Stephan Achenbach
- Department of Cardiology, Friedrich-Alexander-Universität Erlangen-Nürnberg, Maximilianspl 2, 91054 Erlangen, Germany
| | - Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- Acute Vascular Imaging Centre, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- British Heart Foundation Centre of Research Excellence, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
- National Institute of Health Research (NIHR), Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headley Way, Oxford OX39DU, Oxford UK
| |
Collapse
|
41
|
Feher A, Boutagy NE, Oikonomou EK, Thorn S, Liu YH, Miller EJ, Sinusas AJ, Hinchcliff M. Impaired Myocardial Flow Reserve on 82Rubidium Positron Emission Tomography/Computed Tomography in Patients With Systemic Sclerosis. J Rheumatol 2021; 48:1574-1582. [PMID: 34266986 DOI: 10.3899/jrheum.210040] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 07/05/2021] [Indexed: 11/22/2022]
Abstract
OBJECTIVE To investigate the association between Raynaud phenomenon (RP) and coronary microvascular dysfunction, we measured myocardial flow reserve (MFR) using positron emission tomography/computed tomography (PET/CT) in patients with primary and secondary RP and controls. METHODS Patients with RP, patient controls, and healthy participants who underwent dynamic rest-stress 82-rubidium PET/CT were studied. Differences in heart rate-blood pressure product-corrected MFR and clinical predictors of reduced MFR (< 2.0) were determined. RESULTS Forty-nine patients with RP (80% female; aged 65 ± 11 yrs; 11 with primary RP, 18 with systemic sclerosis [SSc], and 20 with other autoimmune rheumatic diseases [AIRDs] including 6 with systemic lupus erythematosus, 6 with rheumatoid arthritis, 4 with overlap syndrome, 2 with Sjögren syndrome, and 2 with inflammatory arthritis), 49 matched patients without RP or AIRD (78% female; 64 ± 13 yrs), and 14 healthy participants (50% female; 35 ± 5 yrs) were studied. Patients with primary RP, matched patient controls, and healthy participants had comparable MFR. Patients with SSc-RP had significantly reduced MFR (1.62 ± 0.32) compared to matched patient controls (P = 0.03, 2.06 ± 0.61) and to healthy participants (P = 0.01, 2.22 ± 0.44). In multivariable logistic regression, SSc was an independent predictor of reduced MFR. We identified a correlation between time since AIRD diagnosis and MFR (r = -0.30, 95% CI -0.63 to -0.02, P = 0.04). CONCLUSION Our findings suggest that only secondary, not primary, RP is associated with reduced MFR, and that patients with SSc-RP have reduced MFR compared to those with primary RP and patients with other AIRDs. Larger prospective studies are warranted to fully elucidate the prognostic value of MFR in patients with secondary RP.
Collapse
Affiliation(s)
- Attila Feher
- A. Feher, MD, PhD, E.K. Oikonomou, MD, PhD, S. Thorn, PhD, Y.H. Liu, PhD, E.J. Miller, MD, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine
| | - Nabil E Boutagy
- N.E. Boutagy, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, and Vascular Biology and Therapeutics Program, and Department of Pharmacology, Yale School of Medicine
| | - Evangelos K Oikonomou
- A. Feher, MD, PhD, E.K. Oikonomou, MD, PhD, S. Thorn, PhD, Y.H. Liu, PhD, E.J. Miller, MD, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine
| | - Stephanie Thorn
- A. Feher, MD, PhD, E.K. Oikonomou, MD, PhD, S. Thorn, PhD, Y.H. Liu, PhD, E.J. Miller, MD, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine
| | - Yi-Hwa Liu
- A. Feher, MD, PhD, E.K. Oikonomou, MD, PhD, S. Thorn, PhD, Y.H. Liu, PhD, E.J. Miller, MD, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine
| | - Edward J Miller
- A. Feher, MD, PhD, E.K. Oikonomou, MD, PhD, S. Thorn, PhD, Y.H. Liu, PhD, E.J. Miller, MD, PhD, Section of Cardiovascular Medicine, Department of Internal Medicine, Yale School of Medicine
| | - Albert J Sinusas
- A.J. Sinusas, MD, BSc, Section of Cardiovascular Medicine, Department of Internal Medicine, and Department of Radiology and Biomedical Imaging, Yale School of Medicine, and Department of Biomedical Engineering, Yale University
| | - Monique Hinchcliff
- M. Hinchcliff, MD, Section of Rheumatology, Department of Internal Medicine, and Department of Internal Medicine, Clinical and Translational Research Accelerator, Yale School of Medicine, New Haven, Connecticut, USA.
| |
Collapse
|
42
|
Antoniades C, Oikonomou EK. Artificial intelligence in cardiovascular imaging-principles, expectations, and limitations. Eur Heart J 2021; 45:ehab678. [PMID: 34557898 PMCID: PMC11015951 DOI: 10.1093/eurheartj/ehab678] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/25/2021] [Revised: 06/22/2021] [Accepted: 09/13/2021] [Indexed: 11/13/2022] Open
Affiliation(s)
- Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, UK
- British Heart Foundation Centre of Research Excellence, Oxford, UK
- National Institute of Health Research (NIHR), Oxford Biomedical Research Centre, Oxford University Hospitals NHS Foundation Trust, John Radcliffe Hospital, Headley Way, Oxford OX39DU, UK
- Acute Vascular Imaging Centre, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, UK
| | - Evangelos K Oikonomou
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Headley Way, Oxford OX39DU, UK
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale-New Haven Hospital, Yale School of Medicine, New Haven, CT, USA
| |
Collapse
|
43
|
Feher A, Boutagy NE, Oikonomou EK, Liu YH, Miller EJ, Sinusas AJ, Hinchcliff M. Association Between Impaired Myocardial Flow Reserve on 82Rubidium Positron Emission Tomography Imaging and Adverse Events in Patients With Autoimmune Rheumatic Disease. Circ Cardiovasc Imaging 2021; 14:e012208. [PMID: 34503339 DOI: 10.1161/circimaging.120.012208] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/16/2022]
Abstract
BACKGROUND Coronary microvascular dysfunction has been described in patients with autoimmune rheumatic disease (ARD). However, it is unknown whether positron emission tomography (PET)-derived myocardial flow reserve (MFR) can predict adverse events in this population. METHODS Patients with ARD without coronary artery disease who underwent dynamic rest-stress 82Rubidium PET were retrospectively studied and compared with patients without ARD matched for age, sex, and comorbidities. The association between MFR and a composite end point of mortality or myocardial infarction or heart failure admission was evaluated with time to event and Cox-regression analyses. RESULTS In 101 patients with ARD (88% female, age: 62±10 years), when compared with matched patients without ARD (n=101), global MFR was significantly reduced (median: 1.68 [interquartile range: 1.34-2.05] versus 1.86 [interquartile range: 1.58-2.28]) and reduced MFR (<1.5) was more frequent (40% versus 22%). MFR did not differ among subtypes of ARDs. In survival analysis, patients with ARD and low MFR (MFR<1.5) had decreased event-free survival for the combined end point, when compared with patients with and without ARD and normal MFR (MFR>1.5) and when compared with patients without ARD and low MFR, after adjustment for the nonlaboratory-based Framingham risk score, rest left ventricular ejection fraction, severe coronary calcification, and the presence of medium/large perfusion defects. In Cox-regression analysis, ARD diagnosis and reduced MFR were both independent predictors of adverse events along with congestive heart failure diagnosis and presence of medium/large stress perfusion defects on PET. Further analysis with inclusion of an interaction term between ARD and impaired MFR revealed no significant interaction effects between ARD and impaired MFR. CONCLUSIONS In our retrospective cohort analysis, patients with ARD had significantly reduced PET MFR compared with age-, sex-, and comorbidity-matched patients without ARD. Reduced PET MFR and ARD diagnosis were both independent predictors of adverse outcomes.
Collapse
Affiliation(s)
- Attila Feher
- Section of Cardiovascular Medicine, Department of Internal Medicine (A.F., E.K.O., Y.-H.L., E.J.M., A.J.S.)
| | - Nabil E Boutagy
- Vascular Biology and Therapeutics Program (N.E.B.).,Department of Pharmacology (N.E.B.)
| | - Evangelos K Oikonomou
- Section of Cardiovascular Medicine, Department of Internal Medicine (A.F., E.K.O., Y.-H.L., E.J.M., A.J.S.)
| | - Yi-Hwa Liu
- Section of Cardiovascular Medicine, Department of Internal Medicine (A.F., E.K.O., Y.-H.L., E.J.M., A.J.S.)
| | - Edward J Miller
- Section of Cardiovascular Medicine, Department of Internal Medicine (A.F., E.K.O., Y.-H.L., E.J.M., A.J.S.)
| | - Albert J Sinusas
- Section of Cardiovascular Medicine, Department of Internal Medicine (A.F., E.K.O., Y.-H.L., E.J.M., A.J.S.).,Department of Radiology and Biomedical Imaging (A.J.S.).,Department of Biomedical Engineering, Yale University, New Haven, CT (A.J.S.)
| | - Monique Hinchcliff
- Section of Rheumatology, Allergy & Immunology, Department of Internal Medicine (M.H.).,Yale School of Medicine, New Haven, CT (M.H.)
| |
Collapse
|
44
|
Oikonomou EK, Siddique M, Antoniades C. Artificial intelligence in medical imaging: A radiomic guide to precision phenotyping of cardiovascular disease. Cardiovasc Res 2021; 116:2040-2054. [PMID: 32090243 DOI: 10.1093/cvr/cvaa021] [Citation(s) in RCA: 36] [Impact Index Per Article: 12.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/19/2019] [Revised: 11/29/2019] [Accepted: 01/23/2020] [Indexed: 12/23/2022] Open
Abstract
ABSTRACT Rapid technological advances in non-invasive imaging, coupled with the availability of large data sets and the expansion of computational models and power, have revolutionized the role of imaging in medicine. Non-invasive imaging is the pillar of modern cardiovascular diagnostics, with modalities such as cardiac computed tomography (CT) now recognized as first-line options for cardiovascular risk stratification and the assessment of stable or even unstable patients. To date, cardiovascular imaging has lagged behind other fields, such as oncology, in the clinical translational of artificial intelligence (AI)-based approaches. We hereby review the current status of AI in non-invasive cardiovascular imaging, using cardiac CT as a running example of how novel machine learning (ML)-based radiomic approaches can improve clinical care. The integration of ML, deep learning, and radiomic methods has revealed direct links between tissue imaging phenotyping and tissue biology, with important clinical implications. More specifically, we discuss the current evidence, strengths, limitations, and future directions for AI in cardiac imaging and CT, as well as lessons that can be learned from other areas. Finally, we propose a scientific framework in order to ensure the clinical and scientific validity of future studies in this novel, yet highly promising field. Still in its infancy, AI-based cardiovascular imaging has a lot to offer to both the patients and their doctors as it catalyzes the transition towards a more precise phenotyping of cardiovascular disease.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK.,Department of Internal Medicine, Yale New Haven Hospital, Yale School of Medicine, New Haven, CT, USA
| | - Musib Siddique
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK.,Caristo Diagnostics Ltd., Oxford, UK
| | - Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, John Radcliffe Hospital, Oxford OX3 9DU, UK.,Oxford Centre of Research Excellence, British Heart Foundation, Oxford, UK.,Oxford Biomedical Research Centre, National Institute of Health Research, Oxford, UK
| |
Collapse
|
45
|
Kotanidis CP, Oikonomou EK, Williams MC, Thomas S, Thomas KE, Nikolaidou C, Dweck MR, Shirodaria C, Neubauer S, Channon KM, Newby DE, Antoniades C. Long-term cardiac risk in individuals with low calcium score on coronary computed tomography angiography can be stratified by the pericoronary fat radiomic profile (FRP). Eur Heart J Cardiovasc Imaging 2021. [DOI: 10.1093/ehjci/jeab111.022] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/15/2022] Open
Abstract
Abstract
Funding Acknowledgements
Type of funding sources: Foundation. Main funding source(s): UKRI, British Heart Foundation
Background
Inflammation in the coronaries induces macroscopic changes in perivascular adipose tissue composition, detectable by the pericoronary Fat Radiomic Profile (FRP) on coronary computed tomography angiography (CCTA).
Purpose
To assess the ability of FRP to stratify cardiac risk in patients with Coronary Artery Calcium (CAC) score below 100 following routine CCTA.
Methods
1,575 participants from the CCTA arm of the SCOT-HEART trial (NCT01149590) eligible for image analysis were included. Pericoronary FRP mapping was performed in perivascular adipose tissue segmentations around the proximal sites of the right and left coronary arteries, as previously validated. We first tested the prognostic value of FRP in the sub-cohort of patients with CAC < 100. We further analysed a sub-group based on the absence of high risk plaque (HRP) features and obstructive coronary artery disease (CAD). The association with future incidence of major adverse cardiac events (MACE: cardiac mortality or non-fatal myocardial infarction) or a composite endpoint of MACE ± late revascularization (MACE-ReVasc) was assessed using adjusted Cox regression models [adjusted for age, sex, systolic blood pressure (SBP), diabetes mellitus (DM), body mass index (BMI), smoking, CAD (≥50% stenosis), total cholesterol, high-density lipoprotein (HDL), and HRP features].
Results
In total, 1,032 patients (53.9% female sex) were found with low CAC score (CAC < 100), with a median age of 55 years. Over a mean follow-up of 4.87 ± 1.06 years, 12 MACE and 47 MACE-ReVasc were recorded. High FRP was associated with a 14.4-fold (95% CI: 3.80-54.78, p < 0.001) higher adjusted risk of MACE and a 2.8-fold (95% CI: 1.49-5.36, p = 0.001) higher adjusted risk of MACE-ReVasc (A). Addition of high FRP to a baseline model consisting of traditional risk factors (age, sex, systolic blood pressure, diabetes mellitus, BMI, smoking, CAD (≥50% stenosis), total cholesterol, HDL, HRP) significantly enhanced (deltaAUC at 5 years:0.15, p = 0.03) the model’s performance and reclassified individuals (NRI = 0.59, p = 0.02, B). Interestingly, after more rigorous filtering of the population by absence of HRP features and obstructive CAD, high FRP remained an independent predictor of MACE (n = 756, Adj.HR = 28.1, p = 0.003).
Conclusion
In individuals with low CAC scores the Fat Radiomic Profile biormarker significantly improves risk prediction for adverse clinical events beyond the current state-of-the-art. Non-invasive profiling of pericoronary adipose tissue using CCTA-derived FRP captures irreversible changes in perivascular adipose tissue composition associated with chronic vascular inflammation and atherosclerotic disease, and can supplement the traditional anatomical assessment of the coronary vasculature with a functional marker of disease activity.
Collapse
Affiliation(s)
- CP Kotanidis
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - EK Oikonomou
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - MC Williams
- University of Edinburgh, British Heart Foundation Centre for Cardiovascular Science, Edinburgh, United Kingdom of Great Britain & Northern Ireland
| | - S Thomas
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - KE Thomas
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - C Nikolaidou
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - MR Dweck
- University of Edinburgh, British Heart Foundation Centre for Cardiovascular Science, Edinburgh, United Kingdom of Great Britain & Northern Ireland
| | - C Shirodaria
- Caristo Diagnostics Ltd, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - S Neubauer
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - KM Channon
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - DE Newby
- University of Edinburgh, British Heart Foundation Centre for Cardiovascular Science, Edinburgh, United Kingdom of Great Britain & Northern Ireland
| | - C Antoniades
- University of Oxford, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, Oxford, United Kingdom of Great Britain & Northern Ireland
| |
Collapse
|
46
|
Oikonomou EK, Van Dijk D, Parise H, Suchard MA, de Lemos J, Antoniades C, Velazquez EJ, Miller EJ, Khera R. A phenomapping-derived tool to personalize the selection of anatomical vs. functional testing in evaluating chest pain (ASSIST). Eur Heart J 2021; 42:2536-2548. [PMID: 33881513 PMCID: PMC8488385 DOI: 10.1093/eurheartj/ehab223] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/17/2021] [Revised: 03/14/2021] [Accepted: 03/31/2021] [Indexed: 11/14/2022] Open
Abstract
AIMS Coronary artery disease is frequently diagnosed following evaluation of stable chest pain with anatomical or functional testing. A more granular understanding of patient phenotypes that benefit from either strategy may enable personalized testing. METHODS AND RESULTS Using participant-level data from 9572 patients undergoing anatomical (n = 4734) vs. functional (n = 4838) testing in the PROMISE (PROspective Multicenter Imaging Study for Evaluation of Chest Pain) trial, we created a topological representation of the study population based on 57 pre-randomization variables. Within each patient's 5% topological neighbourhood, Cox regression models provided individual patient-centred hazard ratios for major adverse cardiovascular events and revealed marked heterogeneity across the phenomap [median 1.11 (10th to 90th percentile: 0.52-2.61]), suggestive of distinct phenotypic neighbourhoods favouring anatomical or functional testing. Based on this risk phenomap, we employed an extreme gradient boosting algorithm in 80% of the PROMISE population to predict the personalized benefit of anatomical vs. functional testing using 12 model-derived, routinely collected variables and created a decision support tool named ASSIST (Anatomical vs. Stress teSting decIsion Support Tool). In both the remaining 20% of PROMISE and an external validation set consisting of patients from SCOT-HEART (Scottish COmputed Tomography of the HEART Trial) undergoing anatomical-first vs. functional-first assessment, the testing strategy recommended by ASSIST was associated with a significantly lower incidence of each study's primary endpoint (P = 0.0024 and P = 0.0321 for interaction, respectively), as well as a harmonized endpoint of all-cause mortality or non-fatal myocardial infarction (P = 0.0309 and P < 0.0001 for interaction, respectively). CONCLUSION We propose a novel phenomapping-derived decision support tool to standardize the selection of anatomical vs. functional testing in the evaluation of stable chest pain, validated in two large and geographically diverse clinical trial populations.
Collapse
Affiliation(s)
- Evangelos K Oikonomou
- Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - David Van Dijk
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
- Department of Computer Science, Yale University, 51 Prospect St, New Haven, CT 06520-8285, USA
| | - Helen Parise
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Marc A Suchard
- Department of Biostatistics, Fielding School of Public Health, University of California, 650 Charles E. Young Drive S, Los Angeles, CA 90095, USA
- Departments of Computational Medicine and Human Genetics, David Geffen School of Medicine at UCLA, University of California, 695 Charles E. Young Drive S, Los Angeles, CA 90095, USA
| | - James de Lemos
- Division of Cardiology, Department of Internal Medicine, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, Dallas, TX 75390-8830, USA
| | - Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Level 6, West Wing, John Radcliffe Hospital, Headley Way, OX3 9DU, Oxford, UK
| | - Eric J Velazquez
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Edward J Miller
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
| | - Rohan Khera
- Section of Cardiovascular Medicine, Department of Internal Medicine, Yale University School of Medicine, 333 Cedar Street, New Haven, CT 06520-8056, USA
- Center for Outcomes Research and Evaluation, Yale-New Haven Hospital, MS 1 Church Street, Suite 200, New Haven, CT 06510, USA
| |
Collapse
|
47
|
Akoumianakis I, Badi I, Douglas G, Chuaiphichai S, Herdman L, Akawi N, Margaritis M, Antonopoulos AS, Oikonomou EK, Psarros C, Galiatsatos N, Tousoulis D, Kardos A, Sayeed R, Krasopoulos G, Petrou M, Schwahn U, Wohlfart P, Tennagels N, Channon KM, Antoniades C. Insulin-induced vascular redox dysregulation in human atherosclerosis is ameliorated by dipeptidyl peptidase 4 inhibition. Sci Transl Med 2021; 12:12/541/eaav8824. [PMID: 32350133 DOI: 10.1126/scitranslmed.aav8824] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/13/2018] [Revised: 10/01/2019] [Accepted: 04/01/2020] [Indexed: 12/12/2022]
Abstract
Recent clinical trials have revealed that aggressive insulin treatment has a neutral effect on cardiovascular risk in patients with diabetes despite improved glycemic control, which may suggest confounding direct effects of insulin on the human vasculature. We studied 580 patients with coronary atherosclerosis undergoing coronary artery bypass surgery (CABG), finding that high endogenous insulin was associated with reduced nitric oxide (NO) bioavailability ex vivo in vessels obtained during surgery. Ex vivo experiments with human internal mammary arteries and saphenous veins obtained from 94 patients undergoing CABG revealed that both long-acting insulin analogs and human insulin triggered abnormal responses of post-insulin receptor substrate 1 downstream signaling ex vivo, independently of systemic insulin resistance status. These abnormal responses led to reduced NO bioavailability, activation of NADPH oxidases, and uncoupling of endothelial NO synthase. Treatment with an oral dipeptidyl peptidase 4 inhibitor (DPP4i) in vivo or DPP4i administered to vessels ex vivo restored physiological insulin signaling, reversed vascular insulin responses, reduced vascular oxidative stress, and improved endothelial function in humans. The detrimental effects of insulin on vascular redox state and endothelial function as well as the insulin-sensitizing effect of DPP4i were also validated in high-fat diet-fed ApoE-/- mice treated with DPP4i. High plasma DPP4 activity and high insulin were additively related with higher cardiac mortality in patients with coronary atherosclerosis undergoing CABG. These findings may explain the inability of aggressive insulin treatment to improve cardiovascular outcomes, raising the question whether vascular insulin sensitization with DPP4i should precede initiation of insulin treatment and continue as part of a long-term combination therapy.
Collapse
Affiliation(s)
- Ioannis Akoumianakis
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Ileana Badi
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Gillian Douglas
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Surawee Chuaiphichai
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Laura Herdman
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Nadia Akawi
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Marios Margaritis
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Alexios S Antonopoulos
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Evangelos K Oikonomou
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Costas Psarros
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | | | - Dimitris Tousoulis
- First Cardiology Clinic, Athens University Medical School, Athens 115 27, Greece
| | - Attila Kardos
- Milton Keynes University Hospital NHS Foundation Trust and Faculty of Life Sciences, University of Buckingham, Buckingham MK6 5LD, UK
| | - Rana Sayeed
- Cardiothoracic Surgery Department, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - George Krasopoulos
- Cardiothoracic Surgery Department, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Mario Petrou
- Cardiothoracic Surgery Department, Oxford University Hospitals NHS Foundation Trust, Oxford OX3 9DU, UK
| | - Uwe Schwahn
- Sanofi Aventis Deutschland GmbH, Frankfurt D-65926, Germany
| | | | | | - Keith M Channon
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK
| | - Charalambos Antoniades
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford OX3 9DU, UK.
| |
Collapse
|
48
|
Simantiris S, Antonopoulos AS, Angelopoulos A, Papanikolaou P, Oikonomou EK, Vamvakaris K, Koumpoura A, Farmaki M, Trivella M, Vlachopoulos C, Tsioufis K, Antoniades C, Tousoulis D. Prognostic value of vascular inflammation biomarkers over clinical risk factors for cardiovascular risk : a meta-analysis. Eur J Prev Cardiol 2021. [DOI: 10.1093/eurjpc/zwab061.243] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/14/2022]
Abstract
Abstract
Funding Acknowledgements
Type of funding sources: None.
Background
Measurement of vascular inflammation biomarkers is supported for estimation of residual inflammatory risk and cardiovascular risk stratification, but to date there is no systematic assessment of the added value of such biomarkers in predicting cardiovascular events and their comparative performance.
Methods
We systematically searched in MEDLINE published literature before Apr 14, 2020 for prospective cohort studies assessing the prognostic value of common biomarkers of vascular inflammation in stable patients with or without cardiovascular disease. The primary outcome was the difference in the c-index (Δ[c-index]) of the best clinical model with the use of inflammatory biomarkers for the prediction of the composite endpoint of major adverse cardiovascular events (MACEs) and mortality. The secondary outcome was the Δ[c-index] for MACEs only. We calculated I² to test heterogeneity. We used random-effects modelling for the meta-analyses to assess the primary and secondary outcome.
Results
We identified 92,507 studies in MEDLINE after duplicates were removed, of which 90,882 (96%) studies were excluded after screening the titles and abstracts, and 1,507 (93%) of the 1,625 remaining studies were excluded after assessment of the full texts. We included 93 (6%) studies in our quantitative evaluation, in which 351,628 individuals participated. The combination of high-risk plaque features and Fat attenuation Index (FAI) by CCTA was associated with the highest prognostic value i.e. Δ[c-index] for the composite endpoint per biomarker type (A). In meta-analysis, both plasma and imaging biomarkers of vascular inflammation offered incremental prognostic value for the primary outcome (pooled estimate for Δ[c-index]% 2.9, 95%CI 2.1-3.6, B) and for MACEs only (pooled estimate for Δ[c-index]% 2.9, 95%CI 2.1-3.8). The prognostic value of imaging biomarkers significantly surpassed that of plasma biomarkers for the primary outcome (Δ[c-index]% 11.3, 95%CI 8.3-14.3 vs. 1.4, 95%CI 0.9-1.8 respectively, p = 1.7x10-10, C). Notably, biomarkers of vascular inflammation offered higher incremental prognostic value in studies with a shorter duration of follow-up (i.e. <5 years), in primary CHD prevention setting and lower cardiovascular risk populations i.e. (studies with <5% cumulative event incidence, D)
Conclusions
The combination of HRP features and FAI by CCTA imaging had the highest prognostic value for cardiovascular events among plasma or imaging biomarkers of vascular inflammation. CCTA imaging to detect residual inflammatory risk and the vulnerable patient at risk for events is a rational approach to improve risk stratification and prognostication.
Abstract Figure.
Collapse
Affiliation(s)
- S Simantiris
- Ippokrateio General Hospital of Athens, Athens, Greece
| | | | | | | | - EK Oikonomou
- Yale University, New Haven, United States of America
| | - K Vamvakaris
- Ippokrateio General Hospital of Athens, Athens, Greece
| | - A Koumpoura
- Ippokrateio General Hospital of Athens, Athens, Greece
| | - M Farmaki
- Ippokrateio General Hospital of Athens, Athens, Greece
| | - M Trivella
- University of Oxford, Oxford, United Kingdom of Great Britain & Northern Ireland
| | | | - K Tsioufis
- Ippokrateio General Hospital of Athens, Athens, Greece
| | - C Antoniades
- University of Oxford, Oxford, United Kingdom of Great Britain & Northern Ireland
| | - D Tousoulis
- Ippokrateio General Hospital of Athens, Athens, Greece
| |
Collapse
|
49
|
Gallegos C, Oikonomou EK, Grimshaw A, Gulati M, Young BD, Miller EJ. Non-steroidal treatment of cardiac sarcoidosis: A systematic review. Int J Cardiol Heart Vasc 2021; 34:100782. [PMID: 33997256 PMCID: PMC8105294 DOI: 10.1016/j.ijcha.2021.100782] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2021] [Revised: 04/03/2021] [Accepted: 04/06/2021] [Indexed: 12/11/2022]
Abstract
The treatment of active cardiac sarcoidosis (CS) usually involves immunosuppressive therapy, with the goal of preventing inflammation-induced scar formation. In most cases, steroids remain the first-line treatment for CS. However, given the side effect profile of their long-term use, steroid-sparing therapies are increasingly used. There are no published randomized trials of steroid-sparing agents in CS. We sought to do a systematic review to evaluate the current published data on the use of non-steroidal treatments in the management of CS. We searched the Cochrane Library, Ovid Medline, Ovid Embase, PubMed, and Web of Science Core Collection databases from inception of database to August 2020 to identify the effectiveness of biological or synthetic disease-modifying antirheumatic agents (s- and bDMARDs). Secondary objectives include safety profile as well as the change in the average corticosteroid dose after treatment initiation. Twenty-three studies were ultimately selected for inclusion which included a total of 480 cases of CS treated with a range of both s- and bDMARDs. In all included studies, sDMARDs and bDMARDs were studied in combination with steroids or as second or higher-line treatments after therapeutic failure or intolerance to corticosteroid use. Methotrexate (MTX) and infliximab (IFX) were the most common synthetic and biologic DMARDs studied respectively, reported in about 35% of the studies reviewed. The use of steroid-sparing agents was associated with a reduction in the maintenance steroid dose used. In conclusion, steroids will remain as the cornerstone of anti-inflammatory management in patients with CS until trials on the use and safety profile of other immunosuppressive agents are completed and published.
Collapse
Affiliation(s)
- Cesia Gallegos
- Yale University School of Medicine, Section of Cardiovascular Medicine, New Haven, CT, USA
| | - Evangelos K Oikonomou
- Yale University School of Medicine, Department of Internal Medicine, New Haven, CT, USA
| | - Alyssa Grimshaw
- Harvey Cushing/John Hay Whitney Medical Library, Yale University, New Haven, CT, USA
| | - Mridu Gulati
- Yale University School of Medicine, Section of Pulmonary, Critical Care & Sleep Medicine, New Haven, CT, USA
| | - Bryan D Young
- Yale University School of Medicine, Section of Cardiovascular Medicine, New Haven, CT, USA
| | - Edward J Miller
- Yale University School of Medicine, Section of Cardiovascular Medicine, New Haven, CT, USA
| |
Collapse
|
50
|
Klüner LV, Oikonomou EK, Antoniades C. Assessing Cardiovascular Risk by Using the Fat Attenuation Index in Coronary CT Angiography. Radiol Cardiothorac Imaging 2021; 3:e200563. [PMID: 33778665 PMCID: PMC7977699 DOI: 10.1148/ryct.2021200563] [Citation(s) in RCA: 19] [Impact Index Per Article: 6.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2020] [Revised: 01/04/2021] [Accepted: 01/20/2021] [Indexed: 01/12/2023]
Abstract
Coronary CT angiography (CCTA) has evolved into a first-line diagnostic test for the investigation of chest pain. Despite advances toward standardizing the reporting of CCTA through the Coronary Artery Disease Reporting and Data System (or CAD-RADS) tool, the prognostic value of CCTA in the earliest stages of atherosclerosis remains limited. Translational work on the bidirectional interplay between the coronary arteries and the perivascular adipose tissue (PVAT) has highlighted PVAT as an in vivo molecular sensor of coronary inflammation. Coronary inflammation is dynamically associated with phenotypic changes in its adjacent PVAT, which can now be detected as perivascular attenuation gradients at CCTA. These gradients are captured and quantified through the fat attenuation index (FAI), a CCTA-based biomarker of coronary inflammation. FAI carries significant prognostic value in both primary and secondary prevention (patients with and without established coronary artery disease) and offers a significant improvement in cardiac risk discrimination beyond traditional risk factors, such as coronary calcium, high-risk plaque features, or the extent of coronary atherosclerosis. Thanks to its dynamic nature, FAI may be used as a marker of disease activity, with observational studies further suggesting that it tracks the response to anti-inflammatory interventions. Finally, radiotranscriptomic studies have revealed complementary radiomic patterns of PVAT, which detect more permanent adverse fibrotic and vascular PVAT remodeling, further expanding the value of PVAT phenotyping as an important readout in modern CCTA analysis. © RSNA, 2021.
Collapse
Affiliation(s)
- Laura V. Klüner
- From the Division of Cardiovascular Medicine (L.V.K., E.K.O., C.A.) and Acute Vascular Imaging Centre (C.A.), Radcliffe Department of Medicine, Level 6, West Wing, University of Oxford, Oxford OX3 9DU, England; and Department of Internal Medicine, School of Medicine, Yale University, New Haven, Conn (E.K.O.)
| | - Evangelos K. Oikonomou
- From the Division of Cardiovascular Medicine (L.V.K., E.K.O., C.A.) and Acute Vascular Imaging Centre (C.A.), Radcliffe Department of Medicine, Level 6, West Wing, University of Oxford, Oxford OX3 9DU, England; and Department of Internal Medicine, School of Medicine, Yale University, New Haven, Conn (E.K.O.)
| | - Charalambos Antoniades
- From the Division of Cardiovascular Medicine (L.V.K., E.K.O., C.A.) and Acute Vascular Imaging Centre (C.A.), Radcliffe Department of Medicine, Level 6, West Wing, University of Oxford, Oxford OX3 9DU, England; and Department of Internal Medicine, School of Medicine, Yale University, New Haven, Conn (E.K.O.)
| |
Collapse
|