A multimodal deep learning model integrating ECG and CXR significantly improved prediction of incident rVHD compared with ECG alone, with the greatest benefit observed for AR.
Abstract
Background: Regurgitant valvular heart disease (rVHD) is a major cause of cardiovascular morbidity. Echocardiography is the diagnostic standard but is resource-intensive for large-scale screening. Electrocardiography (ECG) has shown promise for predicting incident rVHD, yet performance varies across phenotypes, particularly for aortic regurgitation (AR). Chest radiography (CXR) provides complementary structural and hemodynamic information. We hypothesized that a multimodal model integrating ECG and CXR would improve prediction of incident moderate-to-severe rVHD. Methods: In this retrospective multicenter study, we identified 212,888 paired ECG-CXR examinations from 116,380 patients across two Chinese centers. Baseline ECG and CXR were obtained within 60 days of echocardiography. Outcome was progression to moderate-to-severe AR, mitral regurgitation (MR), or tricuspid regurgitation (TR). We developed a multimodal neural network with pretrained unimodal encoders, token-level cross-modal fusion, and a class-specific gating mechanism that adaptively weighted ECG-only, CXR-only, and fused predictions. Performance was assessed using C-index, AUROC, AUPRC, decision curve analysis, net reclassification improvement (NRI), and Kaplan-Meier stratification. Results: Multimodal fusion consistently outperformed unimodal models across all phenotypes. For AR, C-index improved from 0.616 (ECG-only) to 0.713 (multimodal; AUROC 0.729, AUPRC 0.972). For MR, multimodal C-index was 0.801 (AUROC 0.814, AUPRC 0.972), versus 0.782 for ECG and 0.775 for CXR alone. For TR, multimodal and CXR-only models showed similar discrimination (C-index 0.802), but multimodal fusion yielded greater net benefit on decision curve analysis. NRI was positive across all time horizons (1-5 years) for all valve types. Grad-CAM interpretability analyses revealed that ECG attention localized to leads II, V-V (AR), leads I, II, aVF, V-V (MR), and inferior/right precordial leads (TR); CXR attention highlighted chamber-specific enlargement and pulmonary congestion patterns consistent with pathophysiology. Conclusion: A multimodal deep learning model integrating ECG and CXR significantly improved prediction of incident rVHD compared with ECG alone, with the greatest benefit observed for AR. The model leveraged complementary electrical and structural information, demonstrated biological plausibility through interpretability analyses, and provided consistent clinical utility. Given the widespread availability and low cost of both modalities, this approach offers a scalable tool for risk stratification in routine care. Prospective studies are warranted to validate clinical implementation.
A composite artificial intelligence-enabled electrocardiogram (AI-ECG) identified prevalent and predicted incident Structural heart disease (SHD) across multinational cohorts, capturing signals beyond its training targets and supporting its potential as a scalable cardiovascular screening tool.
H. Lee, S. Kang, M. Lee et al.· medRxiv· 0 citations
Background: Heart failure with reduced ejection fraction (HFrEF) remains a major global health burden. Most electrocardiogram (ECG)-based artificial intelligence models are limited to diagnostic tasks or fixed-horizon prognostic classification and provide little insight into the temporal evolution of risk. In addition, concerns regarding model interpretability continue to impede clinical adoption. Whether deep learning applied to ECGs can deliver individualized, time-resolved, and biologically interpretable risk estimates for incident HFrEF across diverse populations remains uncertain. Methods: We developed a convolutional neural network-based survival model using raw 12-lead ECGs from Zhongshan Hospital (SHZS) and externally validated it in independent cohorts from Shanghai Tenth People's Hospital (SHTP) and Beth Israel Deaconess Medical Center (BIDMC). The model generated individualized, day-by-day probabilities of incident HFrEF over a 5-year horizon. Performance was comprehensively evaluated using discrimination, calibration, precision-recall characteristics, clinical utility, and risk stratification metrics, with subgroup analyses across age, sex, and race to assess generalizability. Model interpretability was examined using complementary representation and attention-based frameworks. Results: In 458,884 patients, the survival model demonstrated strong and stable discrimination across cohorts, with overall C-indices of 0.971 (95% CI, 0.965-0.976) in SHZS, 0.945 (95% CI, 0.938-0.950) in SHTP, and 0.855 (95% CI, 0.850-0.860) in BIDMC, and consistently high time-dependent AUROC values across the 1-5-year horizons. Calibration showed close agreement between predicted and observed risks, and decision curve analyses indicated meaningful net clinical benefit across a broad range of thresholds. Kaplan-Meier curves showed clear stratification across predicted risk groups. Interpretability analyses identified physiologically coherent ECG features related to QRS duration, heart rate, and QT interval that were associated with predicted risk. Conclusion: This ECG-based deep learning survival model provides individualized, time-resolved, and clinically interpretable estimates of future HFrEF risk with robust performance across multinational cohorts. These findings support the potential of AI-enabled ECG analysis as an accessible tool for early HFrEF risk stratification within routine clinical workflows.
L. Pan, S. Li, J. Huo et al.· medRxiv· 0 citations
MitralVision reliably distinguishes clinically significant MR using single-view B-mode echocardiography without Doppler input for model inference and may support more standardized MR screening.
R. Sandler, J. Sokol, S.G. Pawar et al.· Journal of the American Soci...· 0 citations
Heart failure (HF) remains a major global cause of morbidity and mortality, where early diagnosis is critical for improving patient outcomes. Conventional single-modality approaches often fail to capture the complex and multifactorial nature of HF. This study investigates the feasibility of a late-fusion framework that integrates modality-specific predictions derived independently from cine-MRI, electrocardiographic signals, biomarkers and demographic data for HF prediction. Independent cine-MRI data from 281 patients, ECG recordings from the PTB-XL PhysioNet database and biomarker profiles from 157 patients were retrospectively analyzed as separate modality-specific cohorts. Twenty-five features were extracted and processed. Modality-specific models (Attention U-Net, MLP, XGBoost) were trained separately on pre-extracted features to preserve predictive accuracy while minimizing computational cost. Their outputs were combined through ensemble meta-learning (XGBoost, LightGBM, Random Forest) with sample weighting to handle missing data. The final HF prediction probability was obtained by averaging the outputs across the three meta-learners. The proposed framework achieved competitive diagnostic performance, with 98.00% (95% CI: 94.96–99.45%) accuracy, 97.80% (95% CI: 92.28–99.73%) sensitivity, 98.17% (95% CI: 93.53–99.78%) specificity, an F1-score of 97.80% (95% CI: 93.6–99.8%) and an AUC of 0.978 (95% CI: 0.945–0.996) when evaluated against state-of-the-art methods. The results highlight the potential of late-fusion strategies for integrating independently trained modality-specific predictions, offering a feasible approach for HF risk assessment under heterogeneous data availability.
Wafa Baccouch, Narjes Benameur, Abdulrahman A. Alsayyari et al.· Technologies· 0 citations
This review critically analyzes recent ECG-based ML/DL models for CVD prediction, with particular attention to model performance, dataset characteristics, preprocessing strategies, and the integration of explainable artificial intelligence (XAI).
Sabit Ahamed Preanto, Md. Hasan Imam Bijoy, Tapon Paul et al.· Discover Artificial Intellig...· 0 citations
PURPOSE OF REVIEW
Artificial intelligence applied to electrocardiography (AI-ECG) has rapidly been investigated in adult cardiovascular medicine, yet translation into pediatric and congenital heart disease populations has lagged. This review summarizes contemporary AI-ECG methodologies and emerging applications in pediatric and congenital heart disease (PCHD), with emphasis on current clinical utility, technical challenges, and future opportunities for implementation.
RECENT FINDINGS
Recent studies demonstrate that deep learning models can accurately identify arrhythmias, ventricular dysfunction, and CHD from standard ECG. Convolutional neural networks remain the dominant architecture, although transformer-based foundation models and self-supervised learning approaches are increasingly being explored. AI-ECG applications in PCHD have expanded from automated interpretation toward proactive risk stratification, including prediction of ventricular dysfunction, mortality, and sudden cardiac death risk. Additional work has investigated wearable monitoring, telemetry analysis, and integration with longitudinal clinical data. Despite promising performance, most studies remain retrospective and single-center, with limited external validation and challenges related to small datasets, physiologic heterogeneity, and age-dependent ECG variation.
SUMMARY
AI-ECG has the potential to transform PCHD by improving diagnostic accuracy, enabling earlier disease detection, and enhancing longitudinal risk assessment. Broader clinical implementation will require multicenter collaboration, prospective validation, standardized datasets, and careful attention to ethical, regulatory, and equity considerations.
David M. Leone, I. Asztalos, J. Mayourian· Current opinion in pediatric...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
