Artificial Intelligence Models Reveal Sex-Specific Gene Expression in Aortic Valve Calcification

Global research trends and hotspots of artificial intelligence research in spinal cord neural injury and restoration-a bibliometrics and visualization analysis

Background

Artificial intelligence (AI) technology has made breakthroughs in spinal cord neural injury and restoration in recent years. It has a positive impact on clinical treatment. This study explores AI research's progress and hotspots in spinal cord neural injury and restoration. It also analyzes research shortcomings related to this area and proposes potential solutions.

Methods

We used CiteSpace 6.1.R6 and VOSviewer 1.6.19 to research WOS articles on AI research in spinal cord neural injury and restoration.

Results

A total of 1,502 articles were screened, in which the United States dominated; Kadone, Hideki (13 articles, University of Tsukuba, JAPAN) was the author with the highest number of publications; ARCH PHYS MED REHAB (IF = 4.3) was the most cited journal, and topics included molecular biology, immunology, neurology, sports, among other related areas.

Conclusion

We pinpointed three research hotspots for AI research in spinal cord neural injury and restoration: (1) intelligent robots and limb exoskeletons to assist rehabilitation training; (2) brain-computer interfaces; and (3) neuromodulation and noninvasive electrical stimulation. In addition, many new hotspots were discussed: (1) starting with image segmentation models based on convolutional neural networks; (2) the use of AI to fabricate polymeric biomaterials to provide the microenvironment required for neural stem cell-derived neural network tissues; (3) AI survival prediction tools, and transcription factor regulatory networks in the field of genetics were discussed. Although AI research in spinal cord neural injury and restoration has many benefits, the technology has several limitations (data and ethical issues). The data-gathering problem should be addressed in future research, which requires a significant sample of quality clinical data to build valid AI models. At the same time, research on genomics and other mechanisms in this field is fragile. In the future, machine learning techniques, such as AI survival prediction tools and transcription factor regulatory networks, can be utilized for studies related to the up-regulation of regeneration-related genes and the production of structural proteins for axonal growth.

Correlation between artificial intelligence-enabled electrocardiogram and echocardiographic features in aortic stenosis

Aims

An artificial intelligence-enabled electrocardiogram (AI-ECG) is a promising tool to detect patients with aortic stenosis (AS) before developing symptoms. However, functional, structural, or haemodynamic components reflected in AI-ECG responsible for its detection are unknown.

Methods and results

The AI-ECG model that was developed at Mayo Clinic using a convolutional neural network to identify patients with moderate-severe AS was applied. In patients used as the testing group, the correlation between the AI-ECG probability of AS and echocardiographic parameters was investigated. This study included 102 926 patients (63.0 ± 16.3 years, 52% male), and 28 464 (27.7%) were identified as AS positive by AI-ECG. Older age, atrial fibrillation, hypertension, diabetes, coronary artery disease, and heart failure were more common in the positive AI-ECG group than in the negative group (P < 0.001). The AI-ECG was correlated with aortic valve area (ρ = -0.48, R² = 0.20), peak velocity (ρ = 0.22, R² = 0.08), and mean pressure gradient (ρ = 0.35, R² = 0.08). The AI-ECG also correlated with left ventricular (LV) mass index (ρ = 0.36, R² = 0.13), E/e' (ρ = 0.36, R² = 0.12), and left atrium volume index (ρ = 0.42, R² = 0.12). Neither LV ejection fraction nor stroke volume index had a significant correlation with the AI-ECG. Age correlated with the AI-ECG (ρ = 0.46, R² = 0.22) and its correlation with echocardiography parameters was similar to that of the AI-ECG.

Conclusion

A combination of AS severity, diastolic dysfunction, and LV hypertrophy is reflected in the AI-ECG to detect AS. There seems to be a gradation of the cardiac anatomical/functional features in the model and its identification process of AS is multifactorial.

Cellular-scale sex differences in extracellular matrix remodeling by valvular interstitial cells

Males acquire calcific aortic valve disease (CAVD) twice as often as females, yet stenotic valves from females display significantly higher levels of fibrosis compared to males with similar extent of disease. Fibrosis occurs as an imbalance between the production and degradation of the extracellular matrix (ECM), specifically type I collagen. This work characterizes ECM production and remodeling by male and female valvular interstitial cells (VICs) to better understand the fibrocalcific divergence between sexes evident in CAVD. Male and female VICs were assessed for gene and protein expression of myofibroblastic markers, ECM components, matrix metalloproteinases (MMPs), and tissue inhibitors of MMPs (TIMPs) via qRT-PCR and western blot. Overall metabolic activity was also measured. Activity assays for collagenase and gelatinase were performed to examine degradation behavior. Male VICs produced greater levels of myofibroblastic markers while female VICs showed greater metabolic activity and collagen production. In general, females displayed a greater level of MMP expression and production than males, but no sex differences were observed in TIMP production. Male VICs also displayed a greater level of collagenase and gelatinase activity than female VICs. This work displays sex differences in ECM remodeling by VICs that could be related to the sexual dimorphism in ECM structure seen in clinical CAVD.

Sex differences in aortic stenosis: Identification of knowledge gaps for sex-specific personalized medicine

Objectives

This review summarizes sex-based differences in aortic stenosis (AS) and identifies knowledge gaps that should be addressed by future studies.

Background

AS is the most common valvular heart disease in developed countries. Sex-specific differences have not been fully appreciated, as a result of widespread under diagnosis of AS in women.

Summary

Studies including sex-stratified analyses have shown differences in pathophysiology with less calcification and more fibrosis in women's aortic valve. Women have impaired myocardial perfusion reserve and different compensatory response of the left ventricle (LV) to pressure overload, with concentric remodeling and more diffuse fibrosis, in contrast to men with more focal fibrosis and more dilated/eccentrically remodeled LV. There is sex difference in clinical presentation and anatomical characteristics, with women having more paradoxical low-flow/low-gradient AS, under-diagnosis and severity underestimated, with less referral to aortic valve replacement (AVR) compared to men. The response to therapies is also different: women have more adverse events with surgical AVR and greater survival benefit with transcatheter AVR. After AVR, women would have more favorable LV remodeling, but sex-related differences in changes in myocardial reserve flow need future research.

Conclusions

Investigation into these described sex-related differences in AS offers potential utility for improving prevention and treatment of AS in women and men. To better understand sex-based differences in pathophysiology, clinical presentation, and response to therapies, sex-specific critical knowledge gaps should be addressed in future research for sex-specific personalized medicine.

Antiphospholipid antibodies in patients with calcific aortic valve stenosis

OBJECTIVES

The antiphospholipid syndrome is defined by antiphospholipid antibodies (aPL) together with arterial and/or venous thromboembolism and/or obstetric morbidities. aPL are overrepresented in SLE and acute myocardial infarction, but it is unknown whether aPL are associated with calcific aortic valve stenosis (CAVS) in the general population. The prevalence of aPL and other SLE-associated autoantibodies and their impact on aortic valve transcriptomics were therefore determined.

METHODS

A total of 233 tricuspid CAVS cases (median age 74, 69% male) and an age- and sex-matched control population were included. aPL were measured as anti-cardiolipin and anti-β2Glycoprotein-I of IgG/M/A isotypes. Resilient, thickened and calcified aortic valve (AV) tissue derived from five aPL positive and five matched aPL negative CAVS patients undergoing surgical aortic valve replacement were analysed by microarrays.

RESULTS

The prevalence of positivity for any aPL (IgG/M/A) in patients with CAVS was 6.4% (95% CI 3.6% - 10.4%: n = 233). aPL IgG was significantly more prevalent in CAVS cases vs controls (4.6% vs 0.6%, P = 0.04). AV tissue from aPL IgG/IgM-positive patients was negatively enriched in pathways related to interferon signalling. One hundred differentially expressed genes could predict local AV CAVS progression with supervised machine learning algorithms.

CONCLUSIONS

aPL IgG was more common in CAVS patients compared with matched controls and aPL positivity was associated with altered AV transcriptomics related to local disease progression and interferon pathways. Further studies should aim to establish aPL as a possible risk marker and/or causal factor for CAVS and could offer new precision therapeutic targets.

The tyrosine kinase inhibitor nilotinib targets discoidin domain receptor 2 in calcific aortic valve stenosis

Background and Purpose

Tyrosine kinase inhibitors (TKI) used to treat chronic myeloid leukaemia (CML) have been associated with cardiovascular side effects, including reports of calcific aortic valve stenosis. The aim of this study was to establish the effects of first and second generation TKIs in aortic valve stenosis and to determine the associated molecular mechanisms.

Experimental Approach

Hyperlipidemic APOE*3Leiden.CETP transgenic mice were treated with nilotinib, imatinib or vehicle. Human valvular interstitial cells (VICs) were isolated and studied in vitro. Gene expression analysis was perfromed in aortic valves from 64 patients undergoing aortic valve replacement surgery.

Key Results

Nilotinib increased murine aortic valve thickness. Nilotinib, but not imatinib, promoted calcification and osteogenic activation and decreased autophagy in human VICs. Differential tyrosine kinase expression was detected between healthy and calcified valve tissue. Transcriptomic target identification revealed that the discoidin domain receptor DDR2, which is preferentially inhibited by nilotinib, was predominantly expressed in human aortic valves but markedly downregulated in calcified valve tissue. Nilotinib and selective DDR2 targeting in VICs induced a similar osteogenic activation, which was blunted by increasing the DDR2 ligand, collagen.

Conclusions and Implications

These findings suggest that inhibition of DDR2 by nilotinib promoted aortic valve thickening and VIC calcification, with possible translational implications for cardiovascular surveillance and possible personalized medicine in CML patients.

Sex-Differences in Aortic Stenosis: Mechanistic Insights and Clinical Implications

Objective

We aim to analyse sex-specific differences in aortic valves (AVs) and valve interstitial cells (VICs) from aortic stenosis (AS) patients.

Approach and Results

238 patients with severe AS undergoing surgical valve replacement were recruited. Two hundred and two AVs (39.1% women) were used for ex vivo analyses and 36 AVs (33.3% women) for in vitro experiments. AVs from men presented increased levels of the inflammatory molecules interleukin (IL)-1β, IL-6, Rantes, and CD45. Oxidative stress (eNOS, myeloperoxidase, malondialdehyde and nitrotyrosine) was upregulated in male AVs. Concerning fibrosis, similar levels of collagen type I, decreased levels of collagen type III and enhanced fibronectin, active Lox-1 and syndecan-1 expressions were found in AVs from men compared with women. Extracellular matrix (ECM) remodeling was characterized by reduced metalloproteinase-1 and 9 expression and increased tissue inhibitor of metalloproteinase-2 expression in male AVs. Importantly, osteogenic markers (bone morphogenetic protein-9, Rank-L, osteopontin, periostin, osteocalcin and Sox-9) and apoptosis (Bax, Caspase 3, p53, and PARP1) were enhanced in AVs from men as compared to women. Isolated male VICs presented higher myofibroblast-like phenotype than female VICs. Male VICs exhibited increased inflammatory, oxidative stress, fibrotic, apoptosis and osteogenic differentiation markers.

Conclusions

Our results suggest that the mechanisms driving the pathogenesis of AS could be different in men and women. Male AVs and isolated VICs presented more inflammation, oxidative stress, ECM remodeling and calcification as compared to those from women. A better knowledge of the pathophysiological pathways in AVs and VICs will allow the development of sex-specific options for the treatment of AS.

Investigating Genetic and Other Determinants of First-Onset Myocardial Infarction in Malaysia: Protocol for the Malaysian Acute Vascular Events Risk Study

BACKGROUND

Although the burden of premature myocardial infarction (MI) is high in Malaysia, direct evidence on the determinants of MI in this multi-ethnic population remains sparse.

OBJECTIVE

The Malaysian Acute Vascular Events Risk (MAVERIK) study is a retrospective case-control study established to investigate the genomic, lipid-related, and other determinants of acute MI in Malaysia. In this paper, we report the study protocol and early results.

METHODS

By June 2019, we had enrolled approximately 2500 patients with their first MI and 2500 controls without cardiovascular disease, who were frequency-matched by age, sex, and ethnicity, from 17 hospitals in Malaysia. For each participant, serum and whole blood have been collected and stored. Clinical, demographic, and behavioral information has been obtained using a 200-item questionnaire.

RESULTS

Tobacco consumption, a history of diabetes, hypertension, markers of visceral adiposity, indicators of lower socioeconomic status, and a family history of coronary disease were more prevalent in cases than in controls. Adjusted (age and sex) logistic regression models for traditional risk factors indicated that current smoking (odds ratio [OR] 4.11, 95% CI 3.56-4.75; P<.001), previous smoking (OR 1.34, 95% CI 1.12-1.60; P=.001), a history of high blood pressure (OR 2.13, 95% CI 1.86-2.44; P<.001), a history of diabetes mellitus (OR 2.72, 95% CI 2.34-3.17; P<.001), a family history of coronary heart disease (OR 1.28, 95% CI 1.07-1.55; P=.009), and obesity (BMI >30 kg/m²; OR 1.19, 95% CI 1.05-1.34; P=.009) were associated with MI in age- and sex-adjusted models.

CONCLUSIONS

The MAVERIK study can serve as a useful platform to investigate genetic and other risk factors for MI in an understudied Southeast Asian population. It should help to hasten the discovery of disease-causing pathways and inform regionally appropriate strategies that optimize public health action.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

RR1-10.2196/31885.

AGTR1, PLTP, and SCG2 associated with immune genes and immune cell infiltration in calcific aortic valve stenosis: analysis from integrated bioinformatics and machine learning

Background: Calcific aortic valve stenosis (CAVS) is a crucial cardiovascular disease facing aging societies. Our research attempts to identify immune-related genes through bioinformatics and machine learning analysis. Two machine learning strategies include Least Absolute Shrinkage Selection Operator (LASSO) and Support Vector Machine Recursive Feature Elimination (SVM-RFE). In addition, we deeply explore the role of immune cell infiltration in CAVS, aiming to study the potential therapeutic targets of CAVS and explore possible drugs. Methods: Download three data sets related to CAVS from the Gene Expression Omnibus. Gene set variation analysis (GSVA) looks for potential mechanisms, determines differentially expressed immune-related genes (DEIRGs) by combining the ImmPort database with CAVS differential genes, and explores the functions and pathways of enrichment. Two machine learning methods, LASSO and SVM-RFE, screen key immune signals and validate them in external data sets. Single-sample GSEA (ssGSEA) and CIBERSORT analyze the subtypes of immune infiltrating cells and integrate the analysis with DEIRGs and key immune signals. Finally, the possible targeted drugs are analyzed through the Connectivity Map (CMap). Results: GSVA analysis of the gene set suggests that it is highly correlated with multiple immune pathways. 266 differential genes (DEGs) integrate with immune genes to obtain 71 DEIRGs. Enrichment analysis found that DEIRGs are related to oxidative stress, synaptic membrane components, receptor activity, and a variety of cardiovascular diseases and immune pathways. Angiotensin II Receptor Type 1(AGTR1), Phospholipid Transfer Protein (PLTP), Secretogranin II (SCG2) are identified as key immune signals of CAVS by machine learning. Immune infiltration found that B cells naï ve and Macrophages M2 are less in CAVS, while Macrophages M0 is more in CAVS. Simultaneously, AGTR1, PLTP, SCG2 are highly correlated with a variety of immune cell subtypes. CMap analysis found that isoliquiritigenin, parthenolide, and pyrrolidine-dithiocarbamate are the top three targeted drugs related to CAVS immunity. Conclusion: The key immune signals, immune infiltration and potential drugs obtained from the research play a vital role in the pathophysiological progress of CAVS.

The Complex Interplay of Inflammation, Metabolism, Epigenetics, and Sex in Calcific Disease of the Aortic Valve

Calcification of the aortic valve is one of the most rapidly increasing pathologies in the aging population worldwide. Traditionally associated to cardiovascular risk conditions, this pathology is still relatively unaddressed on a molecular/cellular standpoint and there are no available treatments to retard its progression unless valve substitution. In this review, we will describe some of the most involved inflammatory players, the metabolic changes that may be responsible of epigenetic modifications and the gender-related differences in the onset of the disease. A better understanding of these aspects and their integration into a unique pathophysiology context is relevant to improve current therapies and patients management.

Trend, predictors, and outcomes of combined mitral valve replacement and coronary artery bypass graft in patients with concomitant mitral valve and coronary artery disease: a National Inpatient Sample database analysis

Aims

Combined mitral valve replacement (MVR) and coronary artery bypass graft (CABG) procedures have been the norm for patients with concomitant mitral valve disease (MVD) and coronary artery disease (CAD) with no large-scale data on their safety and efficacy.

Methods and results

The National Inpatient Sample database (2002-18) was queried to identify patients undergoing MVR and CABG. The major adverse cardiovascular events (MACE) and its components were compared using a propensity score-matched (PSM) analysis to calculate adjusted odds ratios (OR). A total of 6 145 694 patients (CABG only 3 971 045, MVR only 1 933 459, MVR + CABG 241 190) were included in crude analysis, while a matched cohort of 724 237 (CABG only 241 436, MVR only 241 611 vs. MVR + CABG 241 190) was selected in PSM analysis. The combined MVR + CABG procedure had significantly higher adjusted odds of MACE [OR 1.13, 95% confidence interval (CI) 1.11-1.14 and OR 1.96, 95% CI 1.93-1.99] and in-hospital mortality (OR 1.29, 95% CI 1.27-1.31 and OR 2.1, 95% CI 2.05-2.14) compared with CABG alone and MVR alone, respectively. Similarly, the risk of post-procedure bleeding, major bleeding, acute kidney injury, cardiogenic shock, sepsis, need for intra-aortic balloon pump, mean length of stay, and total charges per hospitalization were significantly higher for patients undergoing the combined procedure. These findings remained consistent on yearly trend analysis favouring the isolated CABG and MVR groups.

Conclusion

Combined procedure (MVR + CABG) in patients with MVD and CAD appears to be associated with worse in-hospital outcomes, increased mortality, and higher resource utilization compared with isolated CABG and MVR procedures. Randomized controlled trials are needed to determine the relative safety of these procedures in the full spectrum of baseline valvular and angiographic characteristics.

Artificial Intelligence in Predicting Cardiac Arrest: Scoping Review

BACKGROUND

Cardiac arrest is a life-threatening cessation of activity in the heart. Early prediction of cardiac arrest is important, as it allows for the necessary measures to be taken to prevent or intervene during the onset. Artificial intelligence (AI) technologies and big data have been increasingly used to enhance the ability to predict and prepare for the patients at risk.

OBJECTIVE

This study aims to explore the use of AI technology in predicting cardiac arrest as reported in the literature.

METHODS

A scoping review was conducted in line with the guidelines of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) extension for scoping reviews. Scopus, ScienceDirect, Embase, the Institute of Electrical and Electronics Engineers, and Google Scholar were searched to identify relevant studies. Backward reference list checks of the included studies were also conducted. Study selection and data extraction were independently conducted by 2 reviewers. Data extracted from the included studies were synthesized narratively.

RESULTS

Out of 697 citations retrieved, 41 studies were included in the review, and 6 were added after backward citation checking. The included studies reported the use of AI in the prediction of cardiac arrest. Of the 47 studies, we were able to classify the approaches taken by the studies into 3 different categories: 26 (55%) studies predicted cardiac arrest by analyzing specific parameters or variables of the patients, whereas 16 (34%) studies developed an AI-based warning system. The remaining 11% (5/47) of studies focused on distinguishing patients at high risk of cardiac arrest from patients who were not at risk. Two studies focused on the pediatric population, and the rest focused on adults (45/47, 96%). Most of the studies used data sets with a size of <10,000 samples (32/47, 68%). Machine learning models were the most prominent branch of AI used in the prediction of cardiac arrest in the studies (38/47, 81%), and the most used algorithm was the neural network (23/47, 49%). K-fold cross-validation was the most used algorithm evaluation tool reported in the studies (24/47, 51%).

CONCLUSIONS

AI is extensively used to predict cardiac arrest in different patient settings. Technology is expected to play an integral role in improving cardiac medicine. There is a need for more reviews to learn the obstacles to the implementation of AI technologies in clinical settings. Moreover, research focusing on how to best provide clinicians with support to understand, adapt, and implement this technology in their practice is also necessary.

Implications of Elevated Fibrosis-4 Index in Patients Receiving Trans-Catheter Aortic Valve Replacement

BACKGROUND

The prognostic implication of the fibrosis-4 index, which represents the degree of hepatic injury, on patients receiving trans-catheter aortic valve replacement (TAVR) remains unknown.

METHODS

Patients who underwent TAVR to treat severe aortic stenosis at our institute between 2015 and 2020 were included in this retrospective study and followed for 2 years from the index discharge. The impact of the fibrosis-4 index, which was calculated using age, hepatic enzymes, and platelet count, on 2-year heart failure readmissions was investigated.

RESULTS

A total of 272 patients (median age 85 (82, 88) years old, 76 (28%) men) were included. The median baseline fibrosis-4 index was 2.8 (2.2, 3.7). A high fibrosis-4 index (>3.79) was associated with higher cumulative incidence of the primary endpoint (18% versus 4%, p < 0.001) and higher event rates (0.1041 versus 0.0222 events/year, p < 0.001), with an adjusted hazard ratio of 1.27 (95% confidence interval 1.04-1.54, p = 0.019).

CONCLUSION

an elevated fibrosis-4 index at baseline, indicating the existence of persistent hepatic congestion, was associated with incidences of heart failure following TAVR. Calculating the fibrosis-4 index before TAVR is highly encouraged for risk stratification and shared decision making.

Calcific aortic valve disease: from molecular and cellular mechanisms to medical therapy

Calcific aortic valve disease (CAVD) is a highly prevalent condition that comprises a disease continuum, ranging from microscopic changes to profound fibro-calcific leaflet remodelling, culminating in aortic stenosis, heart failure, and ultimately premature death. Traditional risk factors, such as hypercholesterolaemia and (systolic) hypertension, are shared among atherosclerotic cardiovascular disease and CAVD, yet the molecular and cellular mechanisms differ markedly. Statin-induced low-density lipoprotein cholesterol lowering, a remedy highly effective for secondary prevention of atherosclerotic cardiovascular disease, consistently failed to impact CAVD progression or to improve patient outcomes. However, recently completed phase II trials provide hope that pharmaceutical tactics directed at other targets implicated in CAVD pathogenesis offer an avenue to alter the course of the disease non-invasively. Herein, we delineate key players of CAVD pathobiology, outline mechanisms that entail compromised endothelial barrier function, and promote lipid homing, immune-cell infiltration, and deranged phospho-calcium metabolism that collectively perpetuate a pro-inflammatory/pro-osteogenic milieu in which valvular interstitial cells increasingly adopt myofibro-/osteoblast-like properties, thereby fostering fibro-calcific leaflet remodelling and eventually resulting in left ventricular outflow obstruction. We provide a glimpse into the most promising targets on the horizon, including lipoprotein(a), mineral-binding matrix Gla protein, soluble guanylate cyclase, dipeptidyl peptidase-4 as well as candidates involved in regulating phospho-calcium metabolism and valvular angiotensin II synthesis and ultimately discuss their potential for a future therapy of this insidious disease.

The process of sourcing and preparing EHR data to implement a machine-learning algorithm for early identification of maternal cardiovascular risk (Preprint)

Background

Health care data are fragmenting as patients seek care from diverse sources. Consequently, patient care is negatively impacted by disparate health records. Machine learning (ML) offers a disruptive force in its ability to inform and improve patient care and outcomes. However, the differences that exist in each individual’s health records, combined with the lack of health data standards, in addition to systemic issues that render the data unreliable and that fail to create a single view of each patient, create challenges for ML. Although these problems exist throughout health care, they are especially prevalent within maternal health and exacerbate the maternal morbidity and mortality crisis in the United States.

Objective

This study aims to demonstrate that patient records extracted from the electronic health records (EHRs) of a large tertiary health care system can be made actionable for the goal of effectively using ML to identify maternal cardiovascular risk before evidence of diagnosis or intervention within the patient’s record. Maternal patient records were extracted from the EHRs of a large tertiary health care system and made into patient-specific, complete data sets through a systematic method.

Methods

We outline the effort that was required to define the specifications of the computational systems, the data set, and access to relevant systems, while ensuring that data security, privacy laws, and policies were met. Data acquisition included the concatenation, anonymization, and normalization of health data across multiple EHRs in preparation for their use by a proprietary risk stratification algorithm designed to establish patient-specific baselines to identify and establish cardiovascular risk based on deviations from the patient’s baselines to inform early interventions.

Results

Patient records can be made actionable for the goal of effectively using ML, specifically to identify cardiovascular risk in pregnant patients.

Conclusions

Upon acquiring data, including their concatenation, anonymization, and normalization across multiple EHRs, the use of an ML-based tool can provide early identification of cardiovascular risk in pregnant patients.

The resolvin D1 receptor GPR32 transduces inflammation-resolution and atheroprotection

Chronic inflammation is a hallmark of atherosclerosis and results from an imbalance between pro-inflammatory and pro-resolving signaling. The human GPR32 receptor, together with the ALX/FPR2 receptor, transduces biological actions of several pro-resolving mediators that stimulate resolution of inflammation. However, since no murine homologs of the human GPR32 exist, comprehensive in vivo studies are lacking. Using human atherosclerotic lesions from carotid endarterectomies and creating a transgenic mouse model expressing human GPR32 on a Fpr2×apolipoprotein E double KO background (hGPR32myc×Fpr2-/-×Apoe-/-), we investigated the role of GPR32 in atherosclerosis and self-limiting acute inflammation. GPR32 mRNA was reduced in human atherosclerotic lesions and correlated with the immune cell markers ARG1, NOS2 and FOXP3. Atherosclerotic lesions, necrotic core and aortic inflammation were reduced in hGPR32mycTg×Fpr2-/-×Apoe-/- transgenic mice as compared to Fpr2-/-×Apoe-/- non-transgenic littermates. In a zymosan induced peritonitis model, the hGPR32mycTg×Fpr2-/-×Apoe-/- transgenic mice had reduced inflammation at 4h and enhanced pro-resolving macrophage responses at 24h compared to non-transgenic littermates. The GPR32 agonist aspirin-triggered resolvin D1 (AT-RvD1) regulated leukocyte responses, including enhancing macrophage phagocytosis and intracellular signaling in hGPR32mycTg×Fpr2-/-×Apoe-/- transgenic mice but not in the Fpr2-/-×Apoe-/- non-transgenic littermates. Altogether these results provide the first evidence that GPR32 regulates resolution of inflammation and is atheroprotective in vivo.

Does Oxygen Content Play a Role in Spontaneous Closure of Perimembranous Ventricular Septal Defects?

(1) Background: the impact of a series of laboratory parameters (haemoglobin, haematocrit, foetal haemoglobin, peripheral oxygen saturation, iron, transferrin, ferritin, and albumin) on perimembranous ventricular septal defects spontaneous healing was tested. (2) Methods: one hundred and seven patients were enrolled in the study (57% males; mean age 2.1 ± 0.4 years) and were subsequently subdivided into two groups: self-healing (n = 36) and in need of intervention (n = 71). Self-healing subjects were defined on the basis of an absence of residual shunts at colorDoppler across the previous defect. (3) Results: no statistically significant differences were reported in the size of perimembranous ventricular septal defects between the two groups (p = ns). Conversely, prevalence of anaemia was significantly higher in those requiring intervention than in the self-healing group (p < 0.03), while haemoglobin, iron, ferritin, and albumin levels were lower (p < 0.001, p < 0.05, p < 0.02, p < 0.007, respectively). In multivariable linear regression analysis, only haemoglobin and albumin were found to be associated with spontaneous closure (p < 0.005 and p < 0.02, respectively). In multiple logistic regression analysis, haemoglobin independently increased the probability of self-healing of perimembranous ventricular septal defects (p = 0.03). All patients needing an interventional closure of perimembranous ventricular septal defects presented with haemoglobin <12.7 g/dL. (4) Conclusion: the self-resolution of perimembranous ventricular septal defects seems to rely on numerous factors, including oxygen content, which is likely to promote cell proliferation as well as tissue regeneration. Haemoglobin blood concentration seems to influence the natural history of perimembranous ventricular septal defects and improvement of anaemia by supplementation of iron intake might represent a simple and reliable method to promote self-healing.

Short-Term Event Prediction in the Operating Room (STEP-OP) of Five-Minute Intraoperative Hypotension Using Hybrid Deep Learning: Retrospective Observational Study and Model Development

Background

Intraoperative hypotension has an adverse impact on postoperative outcomes. However, it is difficult to predict and treat intraoperative hypotension in advance according to individual clinical parameters.

Objective

The aim of this study was to develop a prediction model to forecast 5-minute intraoperative hypotension based on the weighted average ensemble of individual neural networks, utilizing the biosignals recorded during noncardiac surgery.

Methods

In this retrospective observational study, arterial waveforms were recorded during noncardiac operations performed between August 2016 and December 2019, at Seoul National University Hospital, Seoul, South Korea. We analyzed the arterial waveforms from the big data in the VitalDB repository of electronic health records. We defined 2s hypotension as the moving average of arterial pressure under 65 mmHg for 2 seconds, and intraoperative hypotensive events were defined when the 2s hypotension lasted for at least 60 seconds. We developed an artificial intelligence–enabled process, named short-term event prediction in the operating room (STEP-OP), for predicting short-term intraoperative hypotension.

Results

The study was performed on 18,813 subjects undergoing noncardiac surgeries. Deep-learning algorithms (convolutional neural network [CNN] and recurrent neural network [RNN]) using raw waveforms as input showed greater area under the precision-recall curve (AUPRC) scores (0.698, 95% CI 0.690-0.705 and 0.706, 95% CI 0.698-0.715, respectively) than that of the logistic regression algorithm (0.673, 95% CI 0.665-0.682). STEP-OP performed better and had greater AUPRC values than those of the RNN and CNN algorithms (0.716, 95% CI 0.708-0.723).

Conclusions

We developed STEP-OP as a weighted average of deep-learning models. STEP-OP predicts intraoperative hypotension more accurately than the CNN, RNN, and logistic regression models.

Trial Registration

ClinicalTrials.gov NCT02914444; https://clinicaltrials.gov/ct2/show/NCT02914444.

Incidence, associated outcomes, and predictors of upper gastrointestinal bleeding following acute myocardial infarction: a SWEDEHEART-based nationwide cohort study

Aims

Of all spontaneous bleeding complications in patients with acute myocardial infarction (MI), upper gastrointestinal bleeding (UGIB) is common and of specific interest since it could be prevented by several prophylactic measures. We aimed to determine the incidence, associated outcomes, and predictors of UGIB following acute MI.

Methods and results

All patients with acute MI enrolled in the SWEDEHEART (Swedish Web-system for Enhancement and Development of Evidence-based care in Heart disease Evaluated According to Recommended Therapies) registry from January 2007 to June 2016 and discharged alive on any antithrombotic therapy (n = 149 477) were followed regarding UGIB for 1 year. Associated outcomes were determined by Cox proportional hazards regression with UGIB as a time-dependent covariate, adjusting for baseline characteristics, invasive treatment, and medical treatment at discharge. Predictors of UGIB were determined by logistic regression and machine learning models.

At 1 year, UGIB had occurred in 2230 patients (cumulative incidence 1.5%) and was significantly associated with an increased risk of all-cause death [hazard ratio (HR) 2.86, 95% confidence interval (CI) 2.58–3.16] and stroke (HR 1.80, 95% CI 1.32–2.45) but not with recurrent MI (HR 1.17, 95% CI 0.97–1.42). The most important predictors of UGIB were haemoglobin, age, systolic blood pressure, blood glucose, smoking status, previous upper gastrointestinal bleeding, and antithrombotic and gastroprotective treatment.

Conclusion

After acute MI, readmission because of UGIB is common and significantly associated with poor prognosis. By using machine learning in addition to traditional logistic regression, new predictors of UGIB, such as blood glucose and smoking status, were identified.