Artificial Intelligence in Cardiovascular Imaging: JACC State-of-the-Art Review

The Digital Revolution in Medicine: Applications in Cardio-Oncology

PURPOSE OF REVIEW

A critical evaluation of contemporary literature regarding the role of big data, artificial intelligence, and digital technologies in precision cardio-oncology care and survivorship, emphasizing innovative and groundbreaking endeavors.

RECENT FINDINGS

Artificial intelligence (AI) algorithm models can automate the risk assessment process and augment current subjective clinical decision tools. AI, particularly machine learning (ML), can identify medically significant patterns in large data sets. Machine learning in cardio-oncology care has great potential in screening, diagnosis, monitoring, and managing cancer therapy-related cardiovascular complications. To this end, large-scale imaging data and clinical information are being leveraged in training efficient AI algorithms that may lead to effective clinical tools for caring for this vulnerable population. Telemedicine may benefit cardio-oncology patients by enhancing healthcare delivery through lowering costs, improving quality, and personalizing care. Similarly, the utilization of wearable biosensors and mobile health technology for remote monitoring holds the potential to improve cardio-oncology outcomes through early intervention and deeper clinical insight. Investigations are ongoing regarding the application of digital health tools such as telemedicine and remote monitoring devices in enhancing the functional status and recovery of cancer patients, particularly those with limited access to centralized services, by increasing physical activity levels and providing access to rehabilitation services.

SUMMARY

In recent years, advances in cancer survival have increased the prevalence of patients experiencing cancer therapy-related cardiovascular complications. Traditional cardio-oncology risk categorization largely relies on basic clinical features and physician assessment, necessitating advancements in machine learning to create objective prediction models using diverse data sources. Healthcare disparities may be perpetuated through AI algorithms in digital health technologies. In turn, this may have a detrimental effect on minority populations by limiting resource allocation. Several AI-powered innovative health tools could be leveraged to bridge the digital divide and improve access to equitable care.

Volatilome and machine learning in ischemic heart disease: Current challenges and future perspectives

Integrating exhaled breath analysis into the diagnosis of cardiovascular diseases holds significant promise as a valuable tool for future clinical use, particularly for ischemic heart disease (IHD). However, current research on the volatilome (exhaled breath composition) in heart disease remains underexplored and lacks sufficient evidence to confirm its clinical validity. Key challenges hindering the application of breath analysis in diagnosing IHD include the scarcity of studies (only three published papers to date), substantial methodological bias in two of these studies, and the absence of standardized protocols for clinical implementation. Additionally, inconsistencies in methodologies-such as sample collection, analytical techniques, machine learning (ML) approaches, and result interpretation-vary widely across studies, further complicating their reproducibility and comparability. To address these gaps, there is an urgent need to establish unified guidelines that define best practices for breath sample collection, data analysis, ML integration, and biomarker annotation. Until these challenges are systematically resolved, the widespread adoption of exhaled breath analysis as a reliable diagnostic tool for IHD remains a distant goal rather than an imminent reality.

Can multiparametric FDG-PET/MRI analysis really enhance the prediction of myocardial recovery after CTO revascularization? A machine learning study

PURPOSE

To comprehensively evaluate the effectiveness of FDG-PET/MRI multiparametric analysis in predicting myocardial wall motion recovery following revascularization of chronic coronary total occlusions (CTO), incorporating both traditional and machine learning approaches.

METHODS

This retrospective study assessed fluorine-18 fluorodeoxyglucose uptake (FDG), late gadolinium enhanced MR imaging (LGE), and MR wall motion abnormalities (WMA) of the left ventricle walls of a clinical cohort with 21 CTO patients (62 ± 9 years, 20 men). All patients were examined using a PET/MRI prior to revascularization and a follow-up cardiac MRI six months later. Prediction models for wall motion recovery after perfusion restoration were developed using linear and nonlinear algorithms as well as multiparametric variables. Performance and prediction explainability were evaluated in a 5x2 cross-validation framework, using ROC AUC and McNemar's test modified for clustered matched-pair data, and Shapley values.

RESULTS

Based on 79 CTO-subtended myocardial wall segments with wall motion abnormalities at baseline, the reference logistic regression model LGE + FDG obtained 0.55(SE = 0.07) in the clustered ROC AUC (cROC AUC) and 0.17(0.05) in the Global Absolute Shapley value. The reference outperformed FDG standalone in cROC AUC (-35(17) %, p < 0.0001), but not LGE standalone (11(12) %, p > 0.05). There were no statistically significant differences between the marginal probabilities of success of these three models. Moreover, no significant improvements (differences < 10 % in cROC AUC, and < 20 % in Global Absolute Shapley, p > 0.05) were found when using mixed effects logistic regression, decision tree, k-nearest neighbor, Naive Bayes, random forest, and support vector machine, with multiparametric combinations of FDG, LGE, and/or WMA.

CONCLUSION

In this clinical cohort, adding more complex interactions between PET/MRI imaging of cardiac function, infarct extension, and/or metabolism did not enhance the prediction of wall motion recovery after perfusion restoration. This finding raises the question whether multiparametric FDG-PET/MRI analysis has demonstrable benefits in risk stratification for CTO revascularization. Further studies with larger cohorts and external validation datasets are crucial to clarify this question and refine the role of multiparametric imaging in this context.

AI-enhanced guidance demonstrated improvement in novices' Apical-4-chamber and Apical-5-chamber views

INTRODUCTION

Artificial Intelligence (AI) modules might simplify the complexities of cardiac ultrasound (US) training by offering real-time, step-by-step guidance on probe manipulation for high-quality diagnostic imaging. This study investigates real-time AI-based guidance tool in facilitating cardiac US training and its impact on novice users' proficiency.

METHODS

This independent, prospective randomized controlled trial enrolled participants who completed a six-hour cardiac US course, followed by a designated cardiac US proficiency exam. Both groups received in-person guided training using the same devices, with the AI-enhanced group receiving additional real-time AI feedback on probe navigation and image quality during both training and testing, while the non-AI group relied solely on the instructor's guidance.

RESULTS

Data were collected from 44 participants: 21 in the AI-enhanced group and 23 in the non-AI group. Improvement was observed in the assessment of the AI-enhanced group compared to the non-AI in acquiring the Apical-4-chamber and the Apical-5- chamber views [mean 88% (± SD 10%) vs. mean 76% (± SD 17%), respectively; p = 0.016]. On the other hand, a slower time to complete the echocardiography exam was observed by the AI-enhanced group [mean 401 s (± SD 51) vs. 348 s (± SD 81) respectively; p = 0.038].

DISCUSSION

The addition of real-time, AI-based feedback demonstrated benefits in the cardiac POCUS teaching process for the more challenging echocardiography four- and five- chamber views. It also has the potential to surpass challenges related to in-person POCUS training. Additional studies are required to explore the long-term effect of this training approach.

CLINICAL TRIAL NUMBER

Not applicable.

Multimodality Imaging of Arrhythmic Risk in Mitral Valve Prolapse

Mitral valve prolapse (MVP) affects 2% to 3% of the general population and is typically benign. However, a subset of patients may develop arrhythmic complications, including sudden cardiac arrest and sudden cardiac death. This review explores the critical role of multimodality imaging in risk stratification for arrhythmic MVP, emphasizing high-risk features such as bileaflet involvement, mitral annular disjunction, the double-peak strain pattern, mechanical dispersion, and myocardial fibrosis. Echocardiography remains the first-line imaging tool for MVP diagnosis, enabling detailed assessment of leaflet morphology, mitral annular disjunction, and mitral regurgitation quantification. Speckle tracking provides insights into abnormal valvular-myocardial mechanics as a potential arrhythmogenic mechanism in MVP. Cardiac magnetic resonance (CMR) offers detailed myocardial tissue characterization through assessment of replacement and interstitial fibrosis using late gadolinium enhancement and T1 mapping/extracellular volume fraction, respectively. Hybrid Positron Emission Tomography/CMR highlights the role of inflammation, which may coexist with fibrosis, in explaining the presence of malignant arrhythmias even with relatively limited fibrosis. The assessment of diffuse fibrosis and inflammation by CMR and Positron Emission Tomography/CMR is particularly valuable in patients without classic imaging risk factors such as mitral annular disjunction, severe mitral regurgitation, or replacement fibrosis. We propose an algorithm integrating clinical, rhythmic, echocardiographic, CMR, and Positron Emission Tomography/CMR parameters for arrhythmic risk stratification and management. Although multimodality imaging is essential for comprehensive risk assessment, most available parameters have not yet been validated in prospective studies nor linked directly to mortality. Consequently, these imaging findings should be interpreted alongside the presence of complex ventricular ectopy, which remains the most robust predictor of mortality in arrhythmic MVP.

The role of artificial intelligence in cardiovascular research: Fear less and live bolder

BACKGROUND

Artificial intelligence (AI) has captured the attention of everyone, including cardiovascular (CV) clinicians and scientists. Moving beyond philosophical debates, modern cardiology cannot overlook AI's growing influence but must actively explore its potential applications in clinical practice and research methodology.

METHODS AND RESULTS

AI offers exciting possibilities for advancing CV medicine by uncovering disease heterogeneity, integrating complex multimodal data, and enhancing treatment strategies. In this review, we discuss the innovative applications of AI in cardiac electrophysiology, imaging, angiography, biomarkers, and genomic data, as well as emerging tools like face recognition and speech analysis. Furthermore, we focus on the expanding role of machine learning (ML) in predicting CV risk and outcomes, outlining a roadmap for the implementation of AI in CV care delivery. While the future of AI holds great promise, technical limitations and ethical challenges remain significant barriers to its widespread clinical adoption.

CONCLUSIONS

Addressing these issues through the development of high-quality standards and involving key stakeholders will be essential for AI to transform cardiovascular care safely and effectively.

Biomarkers and Social Determinants in Atherosclerotic Arterial Diseases: A Scoping Review

BACKGROUND

Arterial diseases like coronary artery disease (CAD), carotid stenosis (CS), peripheral artery disease (PAD), and abdominal aortic aneurysm (AAA) have high morbidity and mortality, making them key research areas. Their multifactorial nature complicates patient treatment and prevention. Biomarkers offer insights into the biochemical and molecular processes, while social factors also significantly impact patients' health and quality of life. This scoping review aims to search the literature for studies that have linked the biological mechanisms of arterial diseases through biomarkers with social issues and to analyze them, supporting the interdependence of biological and social sciences.

METHODS

After a rigorous selection process, adhering to the Preferred Reporting Items for Systematic reviews and Meta-Analyses guidelines for Scoping Reviews, 30 articles were identified through Scopus, Web of Science, and PubMed. Inclusion and exclusion criteria were based on the population, intervention, comparator, outcome, time, and setting framework. Inclusion criteria were studies involving human subjects that explored the relationships among arterial diseases, biomarkers, and psychosocial factors, with no restrictions on publication date. Nonhuman studies, purely biological or medical analyses without psychosocial dimensions, and non-English publications were excluded. Eligible study types included experimental, observational, and review articles published in peer-reviewed journals. Data extraction focused on study characteristics, such as authors, publication year, country, methods, population, and findings. Results were synthesized narratively, as this format was deemed the most suitable for summarizing diverse findings. The quality or methodological rigor of the included studies was not formally assessed, consistent with the scoping review methodology.

RESULTS

In CAD, biomarkers such as high-sensitivity C-reactive protein are strongly associated with psychological stress, whereas lipoprotein (a) and the apolipoprotein B/apolipoprotein A1 ratio reflect lipid profiles that are influenced by socioeconomic factors and ethnicity. In CS, increased carotid intima-media thickness is linked to psychiatric conditions like attention deficit/hyperactivity disorder, and heat shock protein-70 levels are associated with socioeconomic status and gender. In PAD, inflammatory markers, including interleukin-6, intracellular adhesion molecule-1, and high-sensitivity C-reactive protein, mediate the connection between depression and disease severity, with gender and ethnicity influencing the expression of biomarkers and clinical outcomes. In AAA, factors like smoking and exposure to air pollution have increased matrix metalloproteinase levels and other inflammatory markers. Additionally, estradiol provides partial protection in women, underscoring the role of hormones and environmental influences in disease progression. Social determinants such as socioeconomic status, healthcare access, and ethnicity significantly affect biomarker levels and arterial disease progression.

CONCLUSIONS

These findings are crucial for the assumption that social determinants of health modulate the levels of inflammatory biomarkers involved in the progression of arterial diseases such as CAD, CS, PAD, and AAA. This highlights the need to integrate highly predictive mathematical systems into clinical practice, combining biological sciences with social sciences to achieve advanced standards in precision medicine. However, further studies are needed to validate these approaches fully.

The potential role of cardiac CT in ischemic stroke: bridging cardiovascular and cerebrovascular health

Ischemic stroke, accounting for approximately 80% of all stroke cases, remains a leading cause of death and disability worldwide. Effective management of ischemic stroke is heavily influenced by its etiology, which can range from large-artery atherosclerosis and cardiac embolism to cerebral small-vessel occlusions and cryptogenic strokes. Cardioembolic stroke, which makes up about 30% of ischemic strokes, often leads to more severe symptoms and worse outcomes, necessitating anticoagulation therapy for prevention. Cryptogenic strokes, comprising over 25% of ischemic strokes, pose significant challenges for treatment and prevention due to their elusive nature. Thorough investigation of cardioembolic sources during the acute phase of stroke is crucial. While transthoracic and transesophageal echocardiography are traditional methods for detecting intracardiac thrombi and patent foramen ovale (PFO), cardiac CT has emerged as a non-invasive, efficient alternative. Cardiac CT can effectively visualize intracardiac thrombi, PFO, valvular abnormalities, tumors, and complex aortic plaques. This review discusses the potential applications of cardiac CT in ischemic stroke, emphasizing its role in identifying stroke etiology, predicting stroke risk, and assessing patient prognosis. The integration of advanced imaging technologies and artificial intelligence further enhances its diagnostic accuracy and clinical utility, promising to improve outcomes and reduce the healthcare burden associated with ischemic stroke.

Deep learning and radiomics-based vascular calcification characterization in dental cone beam computed tomography as a predictive tool for cardiovascular disease: a proof-of-concept study

OBJECTIVES

This study evaluated an automated deep learning method for detecting calcifications in the extracranial and intracranial carotid arteries and vertebral arteries in cone beam computed tomography (CBCT) scans. Additionally, a model utilizing CBCT-derived radiomics imaging biomarkers was evaluated to predict the cardiovascular diseases (CVD) of stroke and heart attack.

METHODS

Models were trained using the nn-UNet architecture to identify three locations of arterial calcifications: extracranial carotid calcification (ECC), intracranial carotid calcification (ICC), and vertebral artery calcification (VAC). In total, 148 scans were used for model training and validation. Radiomics features extracted from 135 calcification regions were used to characterize arterial calcifications for predicting CVD.

RESULTS

The models demonstrated acceptable performance for detecting regions of calcification for ECC and ICC with bounding box accuracies of 0.71 ± 0.06 and 0.78 ± 0.12 respectively, although VAC performance was lower at 0.53 ± 0.17. Combining clinical data with radiomics for ICC improved stroke predictions, yielding an area under the curve derived from receiver operating characteristic analysis (AUC-ROC) of 0.94 ± 0.09, and combining data for ECC and ICC improved heart attack predictions, with AUC-ROC values of 0.88 ± 0.04 and 0.84 ± 0.16, respectively.

CONCLUSION

Automated, quantifiable methods have potential for detecting ECC and ICC and predicting the incidence of cardiovascular disease based on arterial calcification detection in dental CBCT scans.

Non-invasive derivation of instantaneous free-wave ratio from invasive coronary angiography using a new deep learning artificial intelligence model and comparison with human operators' performance

Invasive coronary physiology is underused and carries risks/costs. Artificial Intelligence (AI) might enable non-invasive physiology from invasive coronary angiography (CAG), possibly outperforming humans, but has seldom been explored, especially for instantaneous wave-free Ratio (iFR). We aimed to develop binary iFR lesion classification AI models and compare them with human performance. single-center retrospective study of patients undergoing CAG and iFR. A validated encoder-decoder convolutional neural network (CNN) performed segmentation. Manual annotation of target vessel and pressure sensor location on a segmented telediastolic frame followed. Three AI models classified lesions as positive (≤ 0.89) or negative (> 0.89). Model 1 uses preprocessed vessel diameters with a transformer. Models 2/3 are EfficientNet-B5 CNNs using concatenated angiography and segmentation - Model 3 employs class-frequency-weighted Cross-Entropy Loss. Previous findings demonstrated Model 3's superiority for left anterior descending (LAD) and Model 1's for circumflex (Cx)/right coronary artery (RCA) - they were therefore unified into a vessel-based model. Ten-fold patient-level cross-validation enabled full sample training/testing. Three experienced operators performed binary iFR classification using single frames of raw/segmented images. Comparison metrics were accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Across 250 measurements, AI accuracy was 72%, PPV 48%, NPV 90%, sensitivity 77%, and specificity 71%. Human accuracy ranged from 54 to 74%. NPV was high for the Cx/RCA (AI: 96/98%; operators: 94/97%), but AI significantly outperformed humans in the LAD (78% vs. 60-64%). An AI model capable of binary iFR lesions classification mildly outperformed interventional cardiologists, supporting further validation studies.

Automated generation of echocardiography reports using artificial intelligence: a novel approach to streamlining cardiovascular diagnostics

Accurate interpretation of echocardiography measurements is essential for diagnosing cardiovascular diseases and guiding clinical management. The emergence of large language models (LLMs) like ChatGPT presents a novel opportunity to automate the generation of echocardiography reports and provide clinical recommendations. This study aimed to evaluate the ability of an LLM (ChatGPT) to 1) generate comprehensive echocardiography reports based solely on provided echocardiographic measurements, and when enriched with clinical information 2) formulate accurate diagnoses, along with appropriate recommendations for further tests, treatment, and follow-up. Echocardiographic data from n = 13 fictional cases (Group 1) and n = 8 clinical cases (Group 2) were input into the LLM. The model's outputs were compared against standard clinical assessments conducted by experienced cardiologists. Using a dedicated scoring system, the LLM's performance was evaluated and stratified based on its accuracy in report generation, diagnostic precision, and the appropriateness of its recommendations. Patterns, frequency and examples of misinterpretations by LLM were analysed. Across all cases, mean total score was 6.86 (SD = 1.12). Group 1 had a mean total score of 6.54 (SD = 1.13) and accuracy of 3.92 (SD = 0.86), while Group 2 scored 7.38 (SD = 0.92) and 4.38 (SD = 0.92), respectively. Recommendations were 2.62 (SD = 0.51) for Group 1 and 3.00 (SD = 0.00) for Group 2, with no significant differences (p = 0.096). Fully acceptable reports were 85.7%, borderline acceptable 14.3%, and none were not acceptable. Of 299 parameters, 5.3% were misinterpreted. The LLM demonstrated a high level of accuracy in generating detailed echocardiography reports, mostly correctly identifying normal and abnormal findings, and making accurate diagnoses across a range of cardiovascular conditions. ChatGPT, as an LLM, shows significant potential in automating the interpretation of echocardiographic data, offering accurate diagnostic insights and clinical recommendations. These findings suggest that LLMs could serve as valuable tools in clinical practice, assisting and streamlining clinical workflow.

Harnessing Electronic Health Records and Artificial Intelligence for Enhanced Cardiovascular Risk Prediction: A Comprehensive Review

Electronic health records (EHR) have revolutionized cardiovascular disease (CVD) research by enabling comprehensive, large-scale, and dynamic data collection. Integrating EHR data with advanced analytical methods, including artificial intelligence (AI), transforms CVD risk prediction and management methodologies. This review examines the advancements and challenges of using EHR in developing CVD prediction models, covering traditional and AI-based approaches. While EHR-based CVD risk prediction has greatly improved, moving from models that integrate real-world data on medication use and imaging, challenges persist regarding data quality, standardization across health care systems, and geographic variability. The complexity of EHR data requires sophisticated computational methods and multidisciplinary approaches for effective CVD risk modeling. AI's deep learning enhances prediction performance but faces limitations in interpretability and the need for validation and recalibration for diverse populations. The future of CVD risk prediction and management increasingly depends on using EHR and AI technologies effectively. Addressing data quality issues and overcoming limitations from retrospective data analysis are critical for improving the reliability and applicability of risk prediction models. Integrating multidimensional data, including environmental, lifestyle, social, and genomic factors, could significantly enhance risk assessment. These models require continuous validation and recalibration to ensure their adaptability to diverse populations and evolving health care environments, providing reassurance about their reliability.

Artificial Intelligence-Driven Assessment of Coronary Computed Tomography Angiography for Intermediate Stenosis: Comparison With Quantitative Coronary Angiography and Fractional Flow Reserve

We aimed to compare artificial intelligence (AI)-based coronary stenosis evaluation of coronary computed tomography angiography (CCTA) with its quantitative counterpart of invasive coronary angiography (ICA) and invasive fractional flow reserve (FFR). This single-center retrospective study included 195 symptomatic patients (mean age 61 ± 10 years, 149 men, 585 coronary arteries) with 215 intermediate coronary lesions, with quantitative coronary angiography (QCA) diameter stenosis ranging from 20% to 80%. An AI-driven research prototype (AI-CCTA) was used to quantify stenosis on CCTA images. The diagnostic accuracy of AI-CCTA was assessed on a per-vessel basis using ICA stenosis grading (with ≥50% stenosis) or invasive FFR (≤0.80) as reference standards. AI-driven diameter stenosis was correlated with the QCA results and expert manual measurements subsequently. The disease prevalence in the 585 coronary arteries, as determined by invasive angiography (≥50%), was 46.5%. AI-CCTA exhibited sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve (AUC) of 71.7%, 89.8%, 85.9%, 78.5%, and 0.81, respectively. The diagnostic performance of AI-CCTA was moderate for the 215 intermediate lesions assessed using QCA and FFR, with an AUC of 0.63 for QCA and FFR. AI-CCTA demonstrated a moderate correlation with QCA (r = 0.42, p <0.001) for measuring the degree of stenosis, which was notably better than the results from manual quantification versus QCA (r = 0.26, p = 0.001). In conclusion, AI-driven CCTA analysis exhibited promising results. AI-CCTA demonstrated a moderate relation with QCA in intermediate coronary stenosis lesions; however, its results surpassed those of manual evaluations.

Application of Machine Learning for Patients With Cardiac Arrest: Systematic Review and Meta-Analysis

BACKGROUND

Currently, there is a lack of effective early assessment tools for predicting the onset and development of cardiac arrest (CA). With the increasing attention of clinical researchers on machine learning (ML), some researchers have developed ML models for predicting the occurrence and prognosis of CA, with certain models appearing to outperform traditional scoring tools. However, these models still lack systematic evidence to substantiate their efficacy.

OBJECTIVE

This systematic review and meta-analysis was conducted to evaluate the prediction value of ML in CA for occurrence, good neurological prognosis, mortality, and the return of spontaneous circulation (ROSC), thereby providing evidence-based support for the development and refinement of applicable clinical tools.

METHODS

PubMed, Embase, the Cochrane Library, and Web of Science were systematically searched from their establishment until May 17, 2024. The risk of bias in all prediction models was assessed using the Prediction Model Risk of Bias Assessment Tool.

RESULTS

In total, 93 studies were selected, encompassing 5,729,721 in-hospital and out-of-hospital patients. The meta-analysis revealed that, for predicting CA, the pooled C-index, sensitivity, and specificity derived from the imbalanced validation dataset were 0.90 (95% CI 0.87-0.93), 0.83 (95% CI 0.79-0.87), and 0.93 (95% CI 0.88-0.96), respectively. On the basis of the balanced validation dataset, the pooled C-index, sensitivity, and specificity were 0.88 (95% CI 0.86-0.90), 0.72 (95% CI 0.49-0.95), and 0.79 (95% CI 0.68-0.91), respectively. For predicting the good cerebral performance category score 1 to 2, the pooled C-index, sensitivity, and specificity based on the validation dataset were 0.86 (95% CI 0.85-0.87), 0.72 (95% CI 0.61-0.81), and 0.79 (95% CI 0.66-0.88), respectively. For predicting CA mortality, the pooled C-index, sensitivity, and specificity based on the validation dataset were 0.85 (95% CI 0.82-0.87), 0.83 (95% CI 0.79-0.87), and 0.79 (95% CI 0.74-0.83), respectively. For predicting ROSC, the pooled C-index, sensitivity, and specificity based on the validation dataset were 0.77 (95% CI 0.74-0.80), 0.53 (95% CI 0.31-0.74), and 0.88 (95% CI 0.71-0.96), respectively. In predicting CA, the most significant modeling variables were respiratory rate, blood pressure, age, and temperature. In predicting a good cerebral performance category score 1 to 2, the most significant modeling variables in the in-hospital CA group were rhythm (shockable or nonshockable), age, medication use, and gender; the most significant modeling variables in the out-of-hospital CA group were age, rhythm (shockable or nonshockable), medication use, and ROSC.

CONCLUSIONS

ML represents a currently promising approach for predicting the occurrence and outcomes of CA. Therefore, in future research on CA, we may attempt to systematically update traditional scoring tools based on the superior performance of ML in specific outcomes, achieving artificial intelligence-driven enhancements.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42024518949; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=518949.

Automated classification of coronary LEsions fRom coronary computed Tomography angiography scans with an updated deep learning model: ALERT study

OBJECTIVES

The use of deep learning models for quantitative measurements on coronary computed tomography angiography (CCTA) may reduce inter-reader variability and increase efficiency in clinical reporting. This study aimed to investigate the diagnostic performance of a recently updated deep learning model (CorEx-2.0) for quantifying coronary stenosis, compared separately with two expert CCTA readers as references.

METHODS

This single-center retrospective study included 50 patients that underwent CCTA to rule out obstructive coronary artery disease between 2017-2022. Two expert CCTA readers and CorEx-2.0 independently assessed all 150 vessels using Coronary Artery Disease-Reporting and Data System (CAD-RADS). Inter-reader agreement analysis and diagnostic performance of CorEx-2.0, compared with each expert reader as references, were evaluated using percent agreement, Cohen's kappa for the binary CAD-RADS classification (CAD-RADS 0-3 versus 4-5) at patient level, and linearly weighted kappa for the 6-group CAD-RADS classification at vessel level.

RESULTS

Overall, 50 patients and 150 vessels were evaluated. Inter-reader agreement using the binary classification at patient level was 91.8% (45/49) with a Cohen's kappa of 0.80. For the 6-group classification at vessel level, inter-reader agreement was 67.6% (100/148) with a linearly weighted kappa of 0.77. CorEx-2.0 showed 100% sensitivity for detecting CAD-RADS ≥ 4 and kappa values of 0.86 versus both readers using the binary classification at patient level. For the 6-group classification at vessel level, CorEx-2.0 demonstrated weighted kappa values of 0.71 versus reader 1 and 0.73 versus reader 2.

CONCLUSION

CorEx-2.0 identified all patients with severe stenosis (CAD-RADS ≥ 4) compared with expert readers and approached expert reader performance at vessel level (weighted kappa > 0.70).

KEY POINTS

Question Can deep learning models improve objectivity in coronary stenosis grading and reporting as coronary CT angiography (CTA) workloads rise? Findings The deep learning model (CorEx-2.0) identified all patients with severe stenoses when compared with expert readers and approached expert reader performance at vessel level. Clinical relevance CorEx-2.0 is a reliable tool for identifying patients with severe stenoses (≥ 70%), underscoring the potential of using this deep learning model to prioritize coronary CTA reading by flagging patients at risk of severe obstructive coronary artery disease.

AI for the hemodynamic assessment of critically ill and surgical patients: focus on clinical applications

Several artificial intelligence (AI)-driven tools have emerged for the hemodynamic evaluation of critically ill and surgical patients. This article provides an overview of current developments and potential clinical applications of machine learning (ML) for blood pressure measurements, hypotension prediction, hemodynamic profiling, and echocardiography. ML algorithms have shown promise in enabling continuous, non-invasive blood pressure monitoring by analyzing pulse oximetry waveforms, though these methods require periodic calibration with traditional oscillometric brachial cuffs. Additionally, a variety of ML models have been trained to forecast impending hypotension. However, clinical research indicates that these algorithms often primarily rely on mean arterial pressure, leading to questions about their added predictive value. The issue of false-positive alerts is also significant and can result in unwarranted clinical interventions. In terms of hemodynamic profiling, ML algorithms have been proposed to automatically classify patients into specific hemodynamic endotypes. However, current evidence suggests these models tend to replicate conventional hemodynamic profiles found in medical textbooks or depicted on advanced hemodynamic monitors. This raises questions about their practical clinical utility, especially given occasional discrepancies that could impact treatment decisions. Point-of-care ultrasound (POCUS) has gained traction for evaluating cardiac function in patients experiencing circulatory shock. ML algorithms now embedded in some POCUS systems can assist by recognizing ultrasound images, guiding users for optimal imaging, automating and reducing the variability of key echocardiographic measurements. These capabilities are especially beneficial for novice operators, potentially enhancing accuracy and confidence in clinical decision-making. In conclusion, while several AI-based technologies show promise for refining hemodynamic assessment in both critically ill and surgical patients, their clinical value varies. Comprehensive validation studies and real-world testing are essential to identify which innovations will genuinely contribute to improving the quality of care.

The role of artificial intelligence in aortic valve stenosis: a bibliometric analysis

Purpose

To explore the expanding role of artificial intelligence (AI) in managing aortic valve stenosis (AVS) by bibliometric analysis to identify research trends, key contributors, and the impact of AI on enhancing diagnostic and therapeutic strategies for AVS.

Methods

A comprehensive literature review was conducted using the Web of Science database, covering publications from January 1990 to March 2024. Articles were analyzed with bibliometric tools such as CiteSpace and VOSviewer to identify key research trends, core authors, institutions, and research hotspots in AI applications for AVS.

Results

A total of 118 articles were analyzed, showing a significant increase in publications from 2014 onwards. The results highlight the growing impact of AI in AVS, particularly in cardiac imaging and predictive modeling. Core authors and institutions, primarily from the U.S. and Germany, are driving research in this field. Key research hotspots include machine learning applications in diagnostics and personalized treatment strategies.

Conclusions

AI is playing a transformative role in the diagnosis and treatment of AVS, improving accuracy and personalizing therapeutic approaches. Despite the progress, challenges such as model transparency and data security remain. Future research should focus on overcoming these challenges while enhancing collaboration among international institutions to further advance AI applications in cardiovascular medicine.

Applications of Artificial Intelligence for the Prediction and Diagnosis of Cancer Therapy-Related Cardiac Dysfunction in Oncology Patients

Cardiovascular diseases and cancer are the leading causes of morbidity and mortality in modern society. Expanding cancer therapies that have improved prognosis may also be associated with cardiotoxicity, and extended life span after survivorship is associated with the increasing prevalence of cardiovascular disease. As such, the field of cardio-oncology has been rapidly expanding, with an aim to identify cardiotoxicity and cardiac disease early in a patient who is receiving treatment for cancer or is in survivorship. Artificial intelligence is revolutionizing modern medicine with its ability to identify cardiac disease early. This article comprehensively reviews applications of artificial intelligence specifically applied to electrocardiograms, echocardiography, cardiac magnetic resonance imaging, and nuclear imaging to predict cardiac toxicity in the setting of cancer therapies, with a view to reduce early complications and cardiac side effects from cancer therapies such as chemotherapy, radiation therapy, or immunotherapy.

An institutional framework to support ethical fair and equitable artificial intelligence augmented care

Coordinated access to multi-domain health data can facilitate the development and implementation of artificial intelligence-augmented clinical decision support (AI-CDS). However, scalable institutional frameworks supporting these activities are lacking. We present the PULSE framework, aimed to establish an integrative and ethically governed ecosystem for the patient-guided, patient-contextualized use of multi-domain health data for AI-augmented care. We describe deliverables related to stakeholder engagement and infrastructure development to support routine engagement of patients for consent-guided data abstraction, pre-processing, and cloud migration to support AI-CDS model development and surveillance. Central focus is placed on the routine collection of social determinants of health and patient self-reported health status to contextualize and evaluate models for fair and equitable use. Inaugural feasibility is reported for over 30,000 consecutively engaged patients. The described framework, conceptually developed to support a multi-site cardiovascular institute, is translatable to other disease domains, offering a validated architecture for use by large-scale tertiary care institutions.

Addressing hidden risks: Systematic review of artificial intelligence biases across racial and ethnic groups in cardiovascular diseases

BACKGROUND

Artificial intelligence (AI)-based models are increasingly being integrated into cardiovascular medicine. Despite promising potential, racial and ethnic biases remain a key concern regarding the development and implementation of AI models in clinical settings.

OBJECTIVE

This systematic review offers an overview of the accuracy and clinical applicability of AI models for cardiovascular diagnosis and prognosis across diverse racial and ethnic groups.

METHOD

A comprehensive literature search was conducted across four medical and scientific databases: PubMed, MEDLINE via Ovid, Scopus, and the Cochrane Library, to evaluate racial and ethnic disparities in cardiovascular medicine.

RESULTS

A total of 1704 references were screened, of which 11 articles were included in the final analysis. Applications of AI-based algorithms across different race/ethnic groups were varied and involved diagnosis, prognosis, and imaging segmentation. Among the 11 studies, 9 (82%) concluded that racial/ethnic bias existed, while 2 (18%) found no differences in the outcomes of AI models across various ethnicities.

CONCLUSION

Our results suggest significant differences in how AI models perform in cardiovascular medicine across diverse racial and ethnic groups.

CLINICAL RELEVANCE STATEMENT

The increasing integration of AI into cardiovascular medicine highlights the importance of evaluating its performance across diverse populations. This systematic review underscores the critical need to address racial and ethnic disparities in AI-based models to ensure equitable healthcare delivery.

Quantitative plaque characterization, pericoronary fat attenuation index, and fractional flow reserve: a novel method for differentiating between stable and unstable angina pectoris in a case-control study

Background

Accurate diagnosis of coronary artery disease is essential for preventing serious cardiovascular events. Although coronary computed tomography angiography (CCTA) is widely used in the clinic, it is limited because it only provides anatomical information, which makes differentiating in-depth between subtypes of noncalcified plaques and assessing the inflammatory state of coronary vessels difficult. Fractional flow reserve with computed tomography (FFR-CT) can be combined with CCTA to form a hybrid anatomic-physiologic diagnostic strategy. This study aimed to improve the recognition of stable and unstable angina with quantitative plaque characteristics, fat attenuation index (FAI), and fractional flow reserve with FFR-CT using a coronary artificial intelligence (AI)-assisted diagnostic system.

Methods

In this retrospective case-control study, 215 and 202 patients with stable and unstable angina pectoris, respectively, who were treated at our hospital between January 2015 and August 2023, were enrolled. Propensity score matching was used to reduce clinical baseline data bias. Binary logistic regression was used to determine the risk factors for unstable angina pectoris. The diagnostic efficacy of quantitative plaque characteristics, pericoronary FAI, FFR-CT, and their combined models in differentiating stable and unstable angina pectoris was determined using the area under the receiver operating characteristic (ROC) curve.

Results

This study included 168 pairs of patients with stable or unstable angina. Patients with unstable angina had a significantly greater pericoronary FAI volume and percentage of, lipid, and fibrolipid components within the total plaque (all P<0.001) and a significantly smaller percentage of calcification components (P<0.001), FFR-CT (P=0.003), and lumen area at the narrowest point of the stenosis(P=0.003) than those with stable angina. Independent risk factors for unstable angina were FAI >-82 Hounsfield units (HU) and total intraplaque lipid component percentage >1.2% (P=0.003 and 0.009, respectively). The area under the curve (AUC) of the ROC regarding pericoronary FAI differentiating between stable and unstable angina was 0.631 (P<0.001). In contrast, the AUC of the combined model of FFR-CT, plaque characteristics, and pericoronary FAI was 0.698 (P<0.001). The AUC value of the combined model was significantly higher than that of the diagnostic model using a single index (all, P<0.001).

Conclusions

AI-assisted diagnostic systems could provide new methods to differentiate between stable and unstable angina. Patients with FAI >-82 HU and total intraplaque lipid component percentage >1.2% had a significantly increased risk of unstable angina, a finding that may be informative for clinical decision-making.

Revolutionizing Cardiology: The Role of Artificial Intelligence in Echocardiography

Background: Artificial intelligence (AI) in echocardiography represents a transformative advancement in cardiology, addressing longstanding challenges in cardiac diagnostics. Echocardiography has traditionally been limited by operator-dependent variability and subjective interpretation, which impact diagnostic reliability. This study evaluates the role of AI, particularly machine learning (ML), in enhancing the accuracy and consistency of echocardiographic image analysis and its potential to complement clinical expertise. Methods: A comprehensive review of existing literature was conducted to analyze the integration of AI into echocardiography. Key AI functionalities, such as image acquisition, standard view classification, cardiac chamber segmentation, structural quantification, and functional assessment, were assessed. Comparisons with traditional imaging modalities like computed tomography (CT), nuclear imaging, and magnetic resonance imaging (MRI) were also explored. Results: AI algorithms demonstrated expert-level accuracy in diagnosing conditions such as cardiomyopathies while reducing operator variability and enhancing diagnostic consistency. The application of ML was particularly effective in automating image analysis and minimizing human error, addressing the limitations of subjective operator expertise. Conclusions: The integration of AI into echocardiography marks a pivotal shift in cardiovascular diagnostics, offering enhanced accuracy, consistency, and reliability. By addressing operator variability and improving diagnostic performance, AI has the potential to elevate patient care and herald a new era in cardiology.

A deep learning model for carotid plaques detection based on CTA images: a two stepwise early-stage clinical validation study

Objective

To develop a deep learning (DL) model for carotid plaque detection based on CTA images and evaluate the clinical application feasibility and value of the model.

Methods

We retrospectively collected data from patients with carotid atherosclerotic plaques who underwent continuous CTA examinations of the head and neck at a tertiary hospital from October 2020 to October 2022. The model combined ResUNet with the Pyramid Scene Parsing Network (PSPNet) to enhance plaque segmentation. Patient plaques were divided into training, validation, and testing sets in a ratio of 7:1.5:1.5. We analyzed recall (lesion-level sensitivity), sensitivity (patient-level), and precision to evaluate the model's diagnostic performance for carotid plaques. The two stepwise early-stage clinical validation study (Comparison study and Model-human study) was used to simulate real clinical plaque diagnostic scenarios.

Results

In total, 647 patients were included in the dataset, including 475 for training, 86 for validation, and 86 for testing. The DL model based on CTA images showed good precision in plaque diagnosis (validation set: precision = 80.49%, sensitivity = 90.70%, recall = 84.62%; test set: precision = 78.37%, sensitivity = 91.86%, recall = 84.58%). In addition, subgroup analysis of the plaque was carried out in the test set. The model had high accuracy in identifying plaques at different locations (Recall: 83.72, 76.32, 89.25, and 83.02%) and with different morphologies (Recall: 86.03, 79.17%). This model also analyzed the results of different types of plaques and showed good to moderate plaque diagnostic accuracy for different plaque types (Recall: 70.00, 86.87, 84.29%). Especially, in the clinical application scenario analysis, the model's diagnostic results for plaques were found to be higher than those of 4 out of 6 radiologists (p < 0.001). Furthermore, in Model-human Real Clinical Scenarios study, we found that the model improved the radiologists' sensitivity in diagnosing plaques. Additionally, the model's diagnostic time for plaques (6 s) was found to be significantly shorter than that all of radiologists (p < 0.001).

Conclusion

This AI model demonstrated strong clinical potential for carotid plaque detection with improved clinician diagnostic performance, shortening time, and practical implementation in real-world clinical cases.

Visualizing hemodynamics: innovative graphical displays and imaging techniques in anesthesia and critical care

The advancements in cardiovascular imaging over the past two decades have been significant. The miniaturization of ultrasound devices has greatly contributed to their widespread adoption in operating rooms and intensive care units. The integration of AI-enabled tools has further transformed the field by simplifying echocardiographic evaluations and enhancing the reproducibility of hemodynamic measurements, even for less experienced operators. Speckle tracking echocardiography offers a direct, visual, and quantitative assessment of myocardial shortening, serving as a compelling alternative to traditional methods for evaluating right and left ventricular systolic function. In critically ill patients, sublingual microcirculation imaging has revealed a high prevalence of microvascular alterations, which are markers of disease severity. The use of handheld vital microscopes enables the quantification of several key parameters, including vessel density, perfusion, red blood cell velocity, and the perfused vascular density. Such metrics are useful for evaluating microcirculatory health. The development of automated software marks a significant advance toward real-time bedside microvascular assessment. These advancements could eventually allow shock resuscitation to be tailored based on microvascular responses. In parallel with imaging advances, cardiac output monitors have evolved significantly. Once cumbersome devices displaying basic numerical data in tabular form, they now feature sleek, touch-screen interfaces integrated with visual decision-support tools. These tools synthesize hemodynamic data into intuitive graphical formats, allowing clinicians to quickly grasp the determinants of circulatory shock. This visual clarity supports more efficient and accurate decision-making, which may ultimately lead to improved patient care and outcomes.

An Automated Machine Learning-Based Quantitative Multiparametric Approach for Mitral Regurgitation Severity Grading

BACKGROUND

Considering the high prevalence of mitral regurgitation (MR) and the highly subjective, variable MR severity reporting, an automated tool that could screen patients for clinically significant MR (≥ moderate) would streamline the diagnostic/therapeutic pathways and ultimately improve patient outcomes.

OBJECTIVES

The authors aimed to develop and validate a fully automated machine learning (ML)-based echocardiography workflow for grading MR severity.

METHODS

ML algorithms were trained on echocardiograms from 2 observational cohorts and validated in patients from 2 additional independent studies. Multiparametric echocardiography core laboratory MR assessment served as ground truth. The machine was trained to measure 16 MR-related parameters. Multiple ML models were developed to find the optimal parameters and preferred ML model for MR severity grading.

RESULTS

The preferred ML model used 9 parameters. Image analysis was feasible in 99.3% of cases and took 80 ± 5 seconds per case. The accuracy for grading MR severity (none to severe) was 0.80, and for significant (moderate or severe) vs nonsignificant MR was 0.97 with a sensitivity of 0.96 and specificity of 0.98. The model performed similarly in cases of eccentric and central MR. Patients graded as having severe MR had higher 1-year mortality (adjusted HR: 5.20 [95% CI: 1.24-21.9]; P = 0.025 compared with mild).

CONCLUSIONS

An automated multiparametric ML model for grading MR severity is feasible, fast, highly accurate, and predicts 1-year mortality. Its implementation in clinical practice could improve patient care by facilitating referral to specialized clinics and access to evidence-based therapies while improving quality and efficiency in the echocardiography laboratory.

Advancements in Artificial Intelligence in Noninvasive Cardiac Imaging: A Comprehensive Review

BACKGROUND

Technological advancements in artificial intelligence (AI) are redefining cardiac imaging by providing advanced tools for analyzing complex health data. AI is increasingly applied across various imaging modalities, including echocardiography, magnetic resonance imaging (MRI), computed tomography (CT), and nuclear imaging, to enhance diagnostic workflows and improve patient outcomes.

HYPOTHESIS

Integrating AI into cardiac imaging enhances image quality, accelerates processing times, and improves diagnostic accuracy, enabling timely and personalized interventions that lead to better health outcomes.

METHODS

A comprehensive literature review was conducted to examine the impact of machine learning and deep learning algorithms on diagnostic accuracy, the detection of subtle patterns and anomalies, and key challenges such as data quality, patient safety, and regulatory barriers.

RESULTS

Findings indicate that AI integration in cardiac imaging enhances image quality, reduces processing times, and improves diagnostic precision, contributing to better clinical decision-making. Emerging machine learning techniques demonstrate the ability to identify subtle cardiac abnormalities that traditional methods may overlook. However, significant challenges persist, including data standardization, regulatory compliance, and patient safety concerns.

CONCLUSIONS

AI holds transformative potential in cardiac imaging, significantly advancing diagnosis and patient outcomes. Overcoming barriers to implementation will require ongoing collaboration among clinicians, researchers, and regulatory bodies. Further research is essential to ensure the safe, ethical, and effective integration of AI in cardiology, supporting its broader application to improve cardiovascular health.

Deep learning for cardiac imaging: focus on myocardial diseases, a narrative review

The integration of computational technologies into cardiology has significantly advanced the diagnosis and management of cardiovascular diseases. Computational cardiology, particularly, through cardiovascular imaging and informatics, enables a precise diagnosis of myocardial diseases utilizing techniques such as echocardiography, cardiac magnetic resonance imaging, and computed tomography. Early-stage disease classification, especially in asymptomatic patients, benefits from these advancements, potentially altering disease progression and improving patient outcomes. Automatic segmentation of myocardial tissue using deep learning (DL) algorithms improves efficiency and consistency in analyzing large patient populations. Radiomic analysis can reveal subtle disease characteristics from medical images and can enhance disease detection, enable patient stratification, and facilitate monitoring of disease progression and treatment response. Radiomic biomarkers have already demonstrated high diagnostic accuracy in distinguishing myocardial pathologies and promise treatment individualization in cardiology, earlier disease detection, and disease monitoring. In this context, this narrative review explores the current state of the art in DL applications in medical imaging (CT, CMR, echocardiography, and SPECT), focusing on automatic segmentation, radiomic feature phenotyping, and prediction of myocardial diseases, while also discussing challenges in integration of DL models in clinical practice.

Designing medical artificial intelligence systems for global use: focus on interoperability, scalability, and accessibility

Advances in artificial intelligence (AI) and machine learning systems promise faster, more efficient, and more personalized care. While many of these models are built on the premise of improving access to the timely screening, diagnosis, and treatment of cardiovascular disease, their validity and accessibility across diverse and international cohorts remain unknown. In this mini-review article, we summarize key obstacles in the effort to design AI systems that will be scalable, accessible, and accurate across distinct geographical and temporal settings. We discuss representativeness, interoperability, quality assurance, and the importance of vendor-agnostic data types that will be available to end-users across the globe. These topics illustrate how the timely integration of these principles into AI development is crucial to maximizing the global benefits of AI in cardiology.

Mitral Regurgitation Evaluation in Modern Echocardiography: Bridging Standard Techniques and Advanced Tools for Enhanced Assessment

Mitral regurgitation (MR) is one of the most common valvular heart diseases worldwide. Echocardiography remains the first line and most effective imaging modality for the diagnosis of mitral valve (MV) pathology and quantitative assessment of MR. The advent of three-dimensional echocardiography has significantly enhanced the evaluation of MV anatomy and function. Furthermore, recent advancements in cardiovascular imaging software have emerged as step-forward tools, providing a powerful support for acquisition, analysis, and interpretation of cardiac ultrasound images in the context of MR. This review aims to provide an overview of the contemporary workflow for echocardiographic assessment of MR, encompassing standard echocardiographic techniques and the integration of semiautomated and automated ultrasound solutions. These novel approaches include advancements in segmentation, phenotyping, morphological quantification, functional grading, and chamber quantification.

Evaluation of myocardial perfusion imaging techniques and artificial intelligence (AI) tools in coronary artery disease (CAD) diagnosis through multi-criteria decision-making method

Background

Cardiovascular diseases (CVDs) continue to be the world's greatest cause of death. To evaluate heart function and diagnose coronary artery disease (CAD), myocardial perfusion imaging (MPI) has become essential. Artificial intelligence (AI) methods have been incorporated into diagnostic methods such as MPI to improve patient outcomes in recent years. This study aims to employ a novel approach to examine how parameters/criteria and performance metrics affect the prioritization of selected MPI techniques and AI tools in CAD diagnosis. Identifying the most effective method in these two interconnected areas will increase the CAD diagnosis rate.

Methods

The study includes an in-depth investigation of popular convolutional neural network (CNN) models, including InceptionV3, VGG16, ResNet50, and DenseNet121, in addition to widely used machine learning (ML) models, including random forests (RF), K-nearest neighbor (KNN), support vector machine (SVM), and Naïve Bayes (NB). In addition, it includes the evaluation of nuclear MPI techniques, including positron emission tomography (PET) and single photon emission computed tomography (SPECT), with the non-nuclear MPI technique of cardiovascular magnetic resonance imaging (CMR). Various performance metrics were used to evaluate AI tools. They are F1-score, recall, specificity, precision, accuracy, and area under the receiver operating characteristic curve (AUC-ROC). For MPI techniques, the evaluation criteria include specificity, sensitivity, radiation dose, cost of scan, and study duration. The analysis was evaluated and compared using the fuzzy-based preference ranking organization method for enrichment evaluation (PROMETHEE), the multi-criteria decision-making method (MDCM).

Results

According to the study's findings, considering selected performance metrics or criteria, RF is the most efficient AI tool for SPECT MPI in the diagnosis of CAD with a net flow (Φnet ) of 0.3778, and it's revealed that CMR is the most efficient MPI technique for CAD diagnosis with a net flow of 0.3666. By expanding this study, more comprehensive evaluations can be made in the diagnosis of CAD.

Conclusions

It was concluded that CMR outperformed the nuclear MPI techniques. SPECT, as the least advantageous technique, remained below average on other criteria except for the cost of the scan. Integrating the RF algorithm, which stands out as the most effective AI tool in diagnosing CAD, with SPECT MPI may contribute to SPECT becoming a superior alternative.

Artificial Intelligence in Fetal and Pediatric Echocardiography

Echocardiography is the main modality in diagnosing acquired and congenital heart disease (CHD) in fetal and pediatric patients. However, operator variability, complex image interpretation, and lack of experienced sonographers and cardiologists in certain regions are the main limitations existing in fetal and pediatric echocardiography. Advances in artificial intelligence (AI), including machine learning (ML) and deep learning (DL), offer significant potential to overcome these challenges by automating image acquisition, image segmentation, CHD detection, and measurements. Despite these promising advancements, challenges such as small number of datasets, algorithm transparency, physician comfort with AI, and accessibility must be addressed to fully integrate AI into practice. This review highlights AI's current applications, challenges, and future directions in fetal and pediatric echocardiography.

Cardiovascular magnetic resonance semi-automated threshold-based post-processing of right ventricular volumes in repaired tetralogy of Fallot

BACKGROUND

Cardiovascular magnetic resonance (CMR) is the gold-standard to estimate right ventricular (RV) volumes, which are key for clinical management of patients with repaired tetralogy of Fallot (rTOF). Semi-automated threshold-based methods (SAT) have been proposed for CMR post-processing as alternatives to fully manual standard tracing. We investigated the impact of SAT on RV analysis using different thresholds in rTOF patients.

METHODS

RV volumes and mass were estimated using SAT and standard fully manual tracing methods in rTOF patients. Two threshold levels were set for SAT, i.e., default 50 (SAT-50) and 30 (SAT-30). RV stroke volumes (SV) were compared to main pulmonary artery forward flow (MPA-FF). Post-processing time, intra- and interobserver variabilities were compared across methods.

RESULTS

Sixty-two CMRs of rTOF patients were analyzed. Compared to the standard fully manual tracing, no significant differences in RV mass, volumes and ejection fraction were observed using SAT-30, whereas SAT-50 significantly underestimated RV end-diastolic-volume index (EDVi) by 10.4% (mean difference of - 11.8 ± 6.2 ml/m2, p 0.03) and overestimated RV mass index by 21.8% (mean difference of 14.2 ± 11.9 g/m2, p 0.002). Compared to MPA-FF, RVSV by standard fully manual method and SAT-30 showed minor biases, respectively, 0.03 ml/m2 and 0.7 ml/m2, while SAT-50 underestimated RVSV by 6.86 ml/m2 (p < 0.001). In six patients, the degree of RV EDVi underestimation by SAT-50 determined a change of category from dilated to non-dilated RV. Intra- and interobserver variabilities were good to excellent for all methods. Post-processing duration was shorter for SAT compared to standard manual segmentation (5.5 ± 1.7 min vs. 19.5 ± 4.4 min, p < 0.001).

CONCLUSION

CMR SAT-30 post-processing is a precise, accurate and time-saving method for biventricular assessment of volumes, ejection fraction and mass in rTOF.

Artificial intelligence: Applications in cardio-oncology and potential impact on racial disparities

Numerous cancer therapies have detrimental cardiovascular effects on cancer survivors. Cardiovascular toxicity can span the course of cancer treatment and is influenced by several factors. To mitigate these risks, cardio-oncology has evolved, with an emphasis on prevention and treatment of cardiovascular complications resulting from the presence of cancer and cancer therapy. Artificial intelligence (AI) holds multifaceted potential to enhance cardio-oncologic outcomes. AI algorithms are currently utilizing clinical data input to identify patients at risk for cardiac complications. Additional application opportunities for AI in cardio-oncology involve multimodal cardiovascular imaging, where algorithms can also utilize imaging input to generate predictive risk profiles for cancer patients. The impact of AI extends to digital health tools, playing a pivotal role in the development of digital platforms and wearable technologies. Multidisciplinary teams have been formed to implement and evaluate the efficacy of these technologies, assessing AI-driven clinical decision support tools. Other avenues similarly support practical application of AI in clinical practice, such as incorporation into electronic health records (EHRs) to detect patients at risk for cardiovascular diseases. While these AI applications may help improve preventive measures and facilitate tailored treatment to patients, they are also capable of perpetuating and exacerbating healthcare disparities, if trained on limited, homogenous datasets. However, if trained and operated appropriately, AI holds substantial promise in positively influencing clinical practice in cardio-oncology. In this review, we explore the impact of AI on cardio-oncology care, particularly regarding predicting cardiotoxicity from cancer treatments, while addressing racial and ethnic biases in algorithmic implementation.

Enhancing Radiologist Efficiency with AI: A Multi-Reader Multi-Case Study on Aortic Dissection Detection and Prioritization

BACKGROUND AND OBJECTIVES

Acute aortic dissection (AD) is a life-threatening condition in which early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep learning (DL)-based application for the automated detection and prioritization of AD on chest CT angiographies (CTAs) with a focus on the reduction in the scan-to-assessment time (STAT) and interpretation time (IT).

MATERIALS AND METHODS

This retrospective Multi-Reader Multi-Case (MRMC) study compared AD detection with and without artificial intelligence (AI) assistance. The ground truth was established by two U.S. board-certified radiologists, while three additional expert radiologists served as readers. Each reader assessed the same CTAs in two phases: assessment unaided by AI assistance (pre-AI arm) and, after a 1-month washout period, assessment aided by device outputs (post-AI arm). STAT and IT metrics were compared between the two arms.

RESULTS

This study included 285 CTAs (95 per reader, per arm) with a mean patient age of 58.5 years ±14.7 (SD), of which 52% were male and 37% had a prevalence of AD. AI assistance significantly reduced the STAT for detecting 33 true positive AD cases from 15.84 min (95% CI: 13.37-18.31 min) without AI to 5.07 min (95% CI: 4.23-5.91 min) with AI, representing a 68% reduction (p < 0.01). The IT also reduced significantly from 21.22 s (95% CI: 19.87-22.58 s) without AI to 14.17 s (95% CI: 13.39-14.95 s) with AI (p < 0.05).

CONCLUSIONS

The integration of a DL-based algorithm for AD detection on chest CTAs significantly reduces both the STAT and IT. By prioritizing urgent cases, the AI-assisted approach outperforms the standard First-In, First-Out (FIFO) workflow.

Diagnostic evaluation of blunt chest trauma by imaging-based application of artificial intelligence

Artificial intelligence (AI) is becoming increasingly integral in clinical practice, such as during imaging tasks associated with the diagnosis and evaluation of blunt chest trauma (BCT). Due to significant advances in imaging-based deep learning, recent studies have demonstrated the efficacy of AI in the diagnosis of BCT, with a focus on rib fractures, pulmonary contusion, hemopneumothorax and others, demonstrating significant clinical progress. However, the complicated nature of BCT presents challenges in providing a comprehensive diagnosis and prognostic evaluation, and current deep learning research concentrates on specific clinical contexts, limiting its utility in addressing BCT intricacies. Here, we provide a review of the available evidence surrounding the potential utility of AI in BCT, and additionally identify the challenges impeding its development. This review offers insights on how to optimize the role of AI in the diagnostic evaluation of BCT, which can ultimately enhance patient care and outcomes in this critical clinical domain.

Artificial Intelligence to Promote Racial and Ethnic Cardiovascular Health Equity

Purpose of Review

The integration of artificial intelligence (AI) in medicine holds promise for transformative advancements aimed at improving healthcare outcomes. Amidst this promise, AI has been envisioned as a tool to detect and mitigate racial and ethnic inequity known to plague current cardiovascular care. However, this enthusiasm is dampened by the recognition that AI itself can harbor and propagate biases, necessitating a careful approach to ensure equity. This review highlights topics in the landscape of AI in cardiology, its role in identifying and addressing healthcare inequities, promoting diversity in research, concerns surrounding its applications, and proposed strategies for fostering equitable utilization.

Recent Findings

Artificial intelligence has proven to be a valuable tool for clinicians in diagnosing and mitigating racial and ethnic inequities in cardiology, as well as the promotion of diversity in research. This promise is counterbalanced by the cautionary reality that AI can inadvertently perpetuate existent biases stemming from limited diversity in training data, inherent biases within datasets, and inadequate bias detection and monitoring mechanisms. Recognizing these concerns, experts emphasize the need for rigorous efforts to address these limitations in the development and deployment of AI within medicine.

Summary

Implementing AI in cardiovascular care to identify and address racial and ethnic inequities requires careful design and execution, beginning with meticulous data collection and a thorough review of training datasets. Furthermore, ensuring equitable performance involves rigorous testing and continuous surveillance of algorithms. Lastly, the promotion of diversity in the AI workforce and engagement of stakeholders are crucial to the advancement of equity to ultimately realize the potential for artificial intelligence for cardiovascular health equity.

[Strategies for prevention and treatment of vascular and nerve injuries in mandibular anterior implant surgery]

Important anatomical structures such as mandibular incisive canal, tongue foramen, and mouth floor vessels may be damaged during implant surgery in the mandibular anterior region, which may lead to mouth floor hematoma, asphyxia, pain, paresthesia and other symptoms. In severe cases, this can be life-threatening. The insufficient alveolar bone space and the anatomical variation of blood vessels and nerves in the mandibular anterior region increase the risk of blood vessel and nerve injury during implant surgery. In case of vascular injury, airway control and hemostasis should be performed, and in case of nerve injury, implant removal and early medical treatment should be performed. To avoid vascular and nerve injury during implant surgery in the mandibular anterior region, it is necessary to be familiar with the anatomical structure, take cone-beam computed tomography, design properly before surgery, and use digital technology during surgery to achieve accurate implant placement. This article summarizes the anatomical structure of the mandibular anterior region, discusses the prevention strategies of vascular and nerve injuries in this region, and discusses the treatment methods after the occurrence of vascular and nerve injuries, to provide clinical reference.

Development and validation of a machine learning-based approach to identify high-risk diabetic cardiomyopathy phenotype

AIMS

Abnormalities in specific echocardiographic parameters and cardiac biomarkers have been reported among individuals with diabetes. However, a comprehensive characterization of diabetic cardiomyopathy (DbCM), a subclinical stage of myocardial abnormalities that precede the development of clinical heart failure (HF), is lacking. In this study, we developed and validated a machine learning-based clustering approach to identify the high-risk DbCM phenotype based on echocardiographic and cardiac biomarker parameters.

METHODS AND RESULTS

Among individuals with diabetes from the Atherosclerosis Risk in Communities (ARIC) cohort who were free of cardiovascular disease and other potential aetiologies of cardiomyopathy (training, n = 1199), unsupervised hierarchical clustering was performed using echocardiographic parameters and cardiac biomarkers of neurohormonal stress and chronic myocardial injury (total 25 variables). The high-risk DbCM phenotype was identified based on the incidence of HF on follow-up. A deep neural network (DeepNN) classifier was developed to predict DbCM in the ARIC training cohort and validated in an external community-based cohort (Cardiovascular Health Study [CHS]; n = 802) and an electronic health record (EHR) cohort (n = 5071). Clustering identified three phenogroups in the derivation cohort. Phenogroup-3 (n = 324, 27% of the cohort) had significantly higher 5-year HF incidence than other phenogroups (12.1% vs. 4.6% [phenogroup 2] vs. 3.1% [phenogroup 1]) and was identified as the high-risk DbCM phenotype. The key echocardiographic predictors of high-risk DbCM phenotype were higher NT-proBNP levels, increased left ventricular mass and left atrial size, and worse diastolic function. In the CHS and University of Texas (UT) Southwestern EHR validation cohorts, the DeepNN classifier identified 16% and 29% of participants with DbCM, respectively. Participants with (vs. without) high-risk DbCM phenotype in the external validation cohorts had a significantly higher incidence of HF (hazard ratio [95% confidence interval] 1.61 [1.18-2.19] in CHS and 1.34 [1.08-1.65] in the UT Southwestern EHR cohort).

CONCLUSION

Machine learning-based techniques may identify 16% to 29% of individuals with diabetes as having a high-risk DbCM phenotype who may benefit from more aggressive implementation of HF preventive strategies.

Development of an artificial intelligence-based algorithm for predicting the severity of myxomatous mitral valve disease from thoracic radiographs by using two grading systems

A heart-convolutional neural network (heart-CNN) was designed and tested for the automatic classification of chest radiographs in dogs affected by myxomatous mitral valve disease (MMVD) at different stages of disease severity. A retrospective and multicenter study was conducted. Lateral radiographs of dogs with concomitant X-ray and echocardiographic examination were selected from the internal databases of two institutions. Dogs were classified as healthy, B1, B2, C and D, based on American College of Veterinary Internal Medicine (ACVIM) guidelines, and as healthy, mild, moderate, severe and late stage, based on Mitral INsufficiency Echocardiographic (MINE) score. Heart-CNN performance was evaluated using confusion matrices, receiver operating characteristic curves, and t-SNE and UMAP analysis. The area under the curve (AUC) was 0.88, 0.88, 0.79, 0.89 and 0.84 for healthy and ACVIM stage B1, B2, C and D, respectively. According to the MINE score, the AUC was 0.90, 0.86, 0.71, 0.82 and 0.82 for healthy, mild, moderate, severe and late stage, respectively. The developed algorithm showed good accuracy in predicting MMVD stages based on both classification systems, proving a potentially useful tool in the early diagnosis of canine MMVD.

Revolutionising Acute Cardiac Care With Artificial Intelligence: Opportunities and Challenges

This article reviews the application of artificial intelligence (AI) in acute cardiac care, highlighting its potential to transform patient outcomes in the face of the global burden of cardiovascular diseases. It explores how AI algorithms can rapidly and accurately process data for the prediction and diagnosis of acute cardiac conditions. The review examines AI's impact on patient health across various diagnostic tools such as echocardiography, electrocardiography, coronary angiography, cardiac computed tomography, and magnetic resonance imaging, discusses the regulatory landscape for AI in health care, and categorises AI algorithms by their risk levels. Furthermore, it addresses the challenges of data quality, generalisability, bias, transparency, and regulatory considerations, underscoring the necessity for inclusive data and robust validation processes. The review concludes with future perspectives on integrating AI into clinical workflows and the ongoing need for research, regulation, and innovation to harness AI's full potential in improving acute cardiac care.

Pharmacogenomics revolutionizing cardiovascular therapeutics: A narrative review

Background and Aim

Among the cardiovascular diseases (CVDs), heart failure, hypertension, and myocardial infarction are associated with the greatest number of disability-adjusted life years due to lifestyle changes and the failure of therapeutic approaches, especially the one-size-fits-all interventions. As a result, there has been advances in defining genetic variants responsible for different responses to cardiovascular drugs such as antiplatelets, anticoagulants, statins, and beta-blockers, which has led to their usage in guiding treatment plans. This study comprehensively reviews the current state-of-the-art potential of pharmacogenomics in dramatically altering CVD treatment. It stresses the applicability of pharmacogenomic technology, the threats associated with its adoption in the clinical setting, and proffers relevant solutions.

Methods

Literature search strategies were used to retrieve articles from various databases: PubMed, Google Scholar, and EBSCOhost. Articles with information relevant to pharmacogenomics, DNA variants, cardiovascular diseases, sequencing techniques, and drug responses were reviewed and analyzed.

Results

DNA-based technologies such as next generation sequencing, whole genome sequencing, whole exome sequencing, and targeted segment sequencing can identify variants in the human genome. This has played a substantial role in identifying different genetic variants governing the poor response and adverse effects associated with cardiovascular drugs. Thus, this has reduced patients' number of emergency visits and hospitalization.

Conclusion

Despite the emergence of pharmacogenomics, its implementation has been threatened by factors including patient compliance and a low adoption rate by clinicians. Education and training programs targeting both healthcare professionals and patients should be established to increase the acceptance and application of the emerging pharmacogenomic technologies in reducing the burden of CVDs.

The Role of Artificial Intelligence and Machine Learning in Cardiovascular Imaging and Diagnosis: Current Insights and Future Directions

Cardiovascular diseases (CVDs) are the major cause of mortality worldwide, emphasizing the critical need for timely and accurate diagnosis. Artificial intelligence (AI) and machine learning (ML) have become revolutionary tools in the healthcare system with significant potential for cardiovascular diagnosis and imaging. AI and ML techniques, including supervised and unsupervised learning, logistic regression, deep learning models, neural networks, and convolutional neural networks (CNNs), have significantly advanced cardiovascular imaging. Applications in echocardiography include left and right ventricular segmentation, ejection fraction measurement, and wall motion analysis. AI and ML hold substantial promise for revolutionizing cardiovascular imaging, demonstrating improvements in diagnostic accuracy and efficiency. This narrative review aims to explore the current applications, advantages, challenges, and future pathways of AI and ML in cardiovascular imaging, highlighting their impact on different imaging modalities and their integration into clinical practice.

The Potential of Artificial Intelligence in Unveiling Healthcare's Future

This article examines the transformative potential of artificial intelligence (AI) in shaping the future of healthcare. It highlights AI's capacity to revolutionize various medical fields, including diagnostics, personalized treatment, drug discovery, telemedicine, and patient care management. Key areas explored include AI's roles in cancer screening, reproductive health, cardiology, outpatient care, laboratory diagnosis, language translation, neuroscience, robotic surgery, radiology, personal healthcare, patient engagement, AI-assisted rehabilitation with exoskeleton robots, and administrative efficiency. The article also addresses challenges to AI adoption, such as privacy concerns, ethical issues, cost barriers, and decision-making authority in patient care. By overcoming these challenges and building trust, AI is positioned to become a critical driver in advancing healthcare, improving outcomes, and meeting the future needs of patients and providers.

A deep learning algorithm for the detection of aortic dissection on non-contrast-enhanced computed tomography via the identification and segmentation of the true and false lumens of the aorta

Background

Aortic dissection is a life-threatening clinical emergency, but it is often missed and misdiagnosed due to the limitations of diagnostic technology. In this study, we developed a deep learning-based algorithm for identifying the true and false lumens in the aorta on non-contrast-enhanced computed tomography (NCE-CT) scans and to ascertain the presence of aortic dissection. Additionally, we compared the diagnostic performance of this algorithm with that of radiologists in detecting aortic dissection.

Methods

We included 320 patients with suspected acute aortic syndrome from three centers (Beijing Anzhen Hospital Affiliated to Capital Medical University, Fujian Provincial Hospital, and Xiangya Hospital of Central South University) between May 2020 and May 2022 in this retrospective study. All patients underwent simultaneous NCE-CT and contrast-enhanced CT (CE-CT). The cohort comprised 160 patients with aortic dissection and 160 without aortic dissection. A deep learning algorithm, three-dimensional (3D) full-resolution U-Net, was continuously trained and refined to segment the true and false lumens of the aorta to determine the presence of aortic dissection. The algorithm's efficacy in detecting dissections was evaluated using the receiver operating characteristic (ROC) curve, including the area under the curve (AUC), sensitivity, and specificity. Furthermore, a comparative analysis of the diagnostic capabilities between our algorithm and three radiologists was conducted.

Results

In diagnosing aortic dissection using NCE-CT images, the developed algorithm demonstrated an accuracy of 93.8% [95% confidence interval (CI): 89.8-98.3%], a sensitivity of 91.6% (95% CI: 86.7-95.8%), and a specificity of 95.6% (95% CI: 91.2-99.3%). In contrast, the radiologists achieved an accuracy of 88.8% (95% CI: 83.5-94.1%), a sensitivity of 90.6% (95% CI: 83.5-94.1%), and a specificity of 94.1% (95% CI: 72.9-97.6%). There was no significant difference between the algorithm's performance and radiologists' mean performance in accuracy, sensitivity, or specificity (P>0.05).

Conclusions

The algorithm proficiently segments the true and false lumens in aortic NCE-CT images, exhibiting diagnostic capabilities comparable to those of radiologists in detecting aortic dissection. This suggests that the algorithm could reduce misdiagnoses in clinical practice, thereby enhancing patient care.

Imaging to Facilitate Ventricular Tachycardia Ablation: Intracardiac Echocardiography, Computed Tomography, Magnetic Resonance, and Positron Emission Tomography

Catheter ablation is a well-established and effective strategy for the management of ventricular tachycardia (VT). However, the identification and characterization of arrhythmogenic substrates for targeted ablation remain challenging. Electrogram abnormalities and responses to pacing during VT provide the classical and most validated methods to identify substrates. However, the 3-dimensional nature of the myocardium, nonconductive tissue, and heterogeneous strands of conductive tissue at the border zones or through the nonconductive zones can prohibit easy electrical sampling and identification of the tissue critical to VT. Intracardiac echocardiography is critical for identification of anatomy, examination of catheter approach and contact, assessment of tissue changes during ablation, and even potential substrates as echogenic regions, but lacks specificity with regard to the latter compared with advanced modalities. In recent decades, cardiac magnetic resonance, computed tomography and positron emission tomography have emerged as valuable tools in the periprocedural evaluation of VT ablation. Cardiac magnetic resonance has unparalleled soft tissue and temporal resolution and excels at identification of expanded interstitial space caused by myocardial infarction, fibrosis, inflammation, or infiltrative myopathies. Computed tomography has excellent spatial resolution and is optimal for identification of anatomic variabilities including wall thickness, thrombus, and lipomatous metaplasia. Positron emission tomography excels at identification of substrates including amyloidosis, sarcoidosis, and other inflammatory substrates. These imaging modalities are vital for assessing arrhythmogenic substrates, guiding optimal access strategy, and assessing ablation efficacy. Although clearly beneficial in specific settings, further clinical trials are needed to enhance generalizability and optimize integration of cardiac imaging for VT ablation.

Atherosclerosis quantification and cardiovascular risk: the ISCHEMIA trial

BACKGROUND AND AIMS

The aim of this study was to determine the prognostic value of coronary computed tomography angiography (CCTA)-derived atherosclerotic plaque analysis in ISCHEMIA.

METHODS

Atherosclerosis imaging quantitative computed tomography (AI-QCT) was performed on all available baseline CCTAs to quantify plaque volume, composition, and distribution. Multivariable Cox regression was used to examine the association between baseline risk factors (age, sex, smoking, diabetes, hypertension, ejection fraction, prior coronary disease, estimated glomerular filtration rate, and statin use), number of diseased vessels, atherosclerotic plaque characteristics determined by AI-QCT, and a composite primary outcome of cardiovascular death or myocardial infarction over a median follow-up of 3.3 (interquartile range 2.2-4.4) years. The predictive value of plaque quantification over risk factors was compared in an area under the curve (AUC) analysis.

RESULTS

Analysable CCTA data were available from 3711 participants (mean age 64 years, 21% female, 79% multivessel coronary artery disease). Amongst the AI-QCT variables, total plaque volume was most strongly associated with the primary outcome (adjusted hazard ratio 1.56, 95% confidence interval 1.25-1.97 per interquartile range increase [559 mm3]; P = .001). The addition of AI-QCT plaque quantification and characterization to baseline risk factors improved the model's predictive value for the primary outcome at 6 months (AUC 0.688 vs. 0.637; P = .006), at 2 years (AUC 0.660 vs. 0.617; P = .003), and at 4 years of follow-up (AUC 0.654 vs. 0.608; P = .002). The findings were similar for the other reported outcomes.

CONCLUSIONS

In ISCHEMIA, total plaque volume was associated with cardiovascular death or myocardial infarction. In this highly diseased, high-risk population, enhanced assessment of atherosclerotic burden using AI-QCT-derived measures of plaque volume and composition modestly improved event prediction.

Deep Learning for Echo Analysis, Tracking, and Evaluation of Mitral Regurgitation (DELINEATE-MR)

BACKGROUND

Artificial intelligence, particularly deep learning (DL), has immense potential to improve the interpretation of transthoracic echocardiography (TTE). Mitral regurgitation (MR) is the most common valvular heart disease and presents unique challenges for DL, including the integration of multiple video-level assessments into a final study-level classification.

METHODS

A novel DL system was developed to intake complete TTEs, identify color MR Doppler videos, and determine MR severity on a 4-step ordinal scale (none/trace, mild, moderate, and severe) using the reading cardiologist as a reference standard. This DL system was tested in internal and external test sets with performance assessed by agreement with the reading cardiologist, weighted κ, and area under the receiver-operating characteristic curve for binary classification of both moderate or greater and severe MR. In addition to the primary 4-step model, a 6-step MR assessment model was studied with the addition of the intermediate MR classes of mild-moderate and moderate-severe with performance assessed by both exact agreement and ±1 step agreement with the clinical MR interpretation.

RESULTS

A total of 61 689 TTEs were split into train (n=43 811), validation (n=8891), and internal test (n=8987) sets with an additional external test set of 8208 TTEs. The model had high performance in MR classification in internal (exact accuracy, 82%; κ=0.84; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR) and external test sets (exact accuracy, 79%; κ=0.80; area under the receiver-operating characteristic curve, 0.98 for moderate or greater MR). Most (63% internal and 66% external) misclassification disagreements were between none/trace and mild MR. MR classification accuracy was slightly higher using multiple TTE views (accuracy, 82%) than with only apical 4-chamber views (accuracy, 80%). In subset analyses, the model was accurate in the classification of both primary and secondary MR with slightly lower performance in cases of eccentric MR. In the analysis of the 6-step classification system, the exact accuracy was 80% and 76% with a ±1 step agreement of 99% and 98% in the internal and external test set, respectively.

CONCLUSIONS

This end-to-end DL system can intake entire echocardiogram studies to accurately classify MR severity and may be useful in helping clinicians refine MR assessments.

Machine-Learning for Phenotyping and Prognostication of Myocardial Infarction and Injury in Suspected Acute Coronary Syndrome

Background

Clinical work-up for suspected acute coronary syndrome (ACS) is resource intensive.

Objectives

This study aimed to develop a machine learning model for digitally phenotyping myocardial injury and infarction and predict 30-day events in suspected ACS patients.

Methods

Training and testing data sets, predominantly derived from electronic health records, included suspected ACS patients presenting to 6 and 26 South Australian hospitals, respectively. All index presentations and 30-day death and myocardial infarction (MI) were adjudicated using the Fourth Universal Definition of MI. We developed 2 diagnostic prediction models which phenotype myocardial injury and infarction according to the Fourth UDMI (chronic myocardial injury vs acute myocardial injury patterns, the latter further differentiated into acute non-ischaemic myocardial injury, Types 1 and 2 MI) using eXtreme Gradient Boosting (XGB) and deep-learning (DL). We also developed an event prediction model for risk prediction of 30-day death or MI using XGB. Analyses were performed in Python 3.6.

Results

The training and testing data sets had 6,722 and 8,869 participants, respectively. The diagnostic prediction XGB and deep learning models achieved an area under the curve of 99.2% ± 0.1% and 98.8% ± 0.2%, respectively, for differentiating an acute myocardial injury pattern from no injury or chronic myocardial injury pattern and achieved 95.5% ± 0.2% and 94.6% ± 0.9%, respectively, for differentiating type 1 MI from type 2 MI or acute nonischemic myocardial injury. The 30-day death/MI event prediction model achieved an area under the curve of 88.5% ± 0.5%.

Conclusions

Machine learning models can digitally phenotype suspected ACS patients at index presentation and predict subsequent events within 30 days. These models require external validation in a randomized clinical trial to evaluate their impact in clinical practice.

Artificial Intelligence in Nuclear Cardiology: An Update and Future Trends

Myocardial perfusion imaging (MPI), using either single photon emission computed tomography (SPECT) or positron emission tomography (PET), is one of the most commonly ordered cardiac imaging tests, with prominent clinical roles for disease diagnosis and risk prediction. Artificial intelligence (AI) could potentially play a role in many steps along the typical MPI workflow, from image acquisition through to clinical reporting and risk estimation. AI can be utilized to improve image quality, reducing radiation exposure and image acquisition times. Once images are acquired, AI can help optimize motion correction and image registration during image reconstruction or provide direct image attenuation correction. Utilizing these image sets, AI can segment a number of anatomic features from associated computed tomographic imaging or even generate synthetic attenuation imaging. Lastly, AI may play an important role in disease diagnosis or risk prediction by combining the large number of potentially important clinical, stress, and imaging-related variables. This review will focus on the most recent developments in the field, providing clinicians and researchers with a timely update on the field. Additionally, it will discuss future trends including applications of AI during multiple points of the typical MPI workflow to maximize clinical utility and methods to maximize the information that can be obtained from hybrid imaging.

Coronary Artery Stenosis and High-Risk Plaque Assessed With an Unsupervised Fully Automated Deep Learning Technique

Background

Coronary computed tomography angiography (CCTA) has emerged as a reliable noninvasive modality to assess coronary artery stenosis and high-risk plaque (HRP). However, CCTA assessment of stenosis and HRP is time-consuming and requires specialized training, limiting its clinical translation.

Objectives

The aim of this study is to develop and validate a fully automated deep learning system capable of characterizing stenosis severity and HRP on CCTA.

Methods

A deep learning system was trained to assess stenosis and HRP on CCTA scans from 570 patients in multiple centers. Stenosis severity was categorized as >0%, 1 to 49%, ≥50%, and ≥70%. HRP was defined as low attenuation plaque (≤30 HU), positive remodeling (≥10% diameter), and spotty calcification (<3 mm). The model was then tested on 769 patients (3,012 vessels) for stenosis severity and 45 patients (325 vessels) for HRP.

Results

Our deep learning system achieved 93.5% per-vessel agreement within 1 Coronary Artery Disease-Reporting and Data System (CAD-RADS) category for stenosis. Diagnostic performance for per-vessel stenosis was very good for sensitivity, specificity, positive predictive value, negative predictive value, and area under the curve with: >0% stenosis: 90.6%, 88.8%, 83.4%, 93.9%, 89.7%, respectively; ≥50% stenosis: 87.1%, 92.3%, 60.9%, 98.1%, 89.7%, respectively. Similarly, the per-vessel HRP feature achieved very good diagnostic performance with an area under the curve of 0.80, 0.79, and 0.77 for low attenuation plaque, spotty calcification, and positive remodeling, respectively.

Conclusions

A fully automated unsupervised deep learning system can rapidly evaluate stenosis severity and characterize HRP with very good diagnostic performance on CCTA.