Key result
AI-enhanced ECG outperforms conventional interpretation for predicting CVD, mortality, and major cardiovascular events.
Why the study?
Although artificial intelligence has expanded the risk-prediction potential of ECG for cardiovascular disease, its incremental prognostic value over conventional non-AI ECG interpretation remains debated.
Do AI/deep learning-enhanced ECG approaches improve the prediction of cardiovascular disease incidence, mortality, and major adverse cardiovascular events compared to conventional ECG approaches across diverse cohorts?
Systematic Review
Do AI/deep learning-enhanced ECG approaches improve the prediction of cardiovascular disease incidence, mortality, and major adverse cardiovascular events compared to conventional ECG approaches across diverse cohorts?
Both conventional and AI-enhanced ECG correlates provide independent prognostic value for cardiovascular events, with AI/deep learning models offering substantially greater incremental predictive performance (ΔAUC ≈ 0.10–0.15) than conventional ECG interpretation (ΔAUC ≈ 0.02–0.06).
Answers are grounded in this paper and cite their sources.
Supports incorporating conventional ECG abnormalities into CVD risk assessment; extends systematic evidence on their prognostic utility alongside AI approaches.
Cardiovascular disease (CVD) is the leading cause of global mortality. Electrocardiography (ECG) is widely accessible and non-invasive, and its abnormalities may carry prognostic value beyond diagnosis. Artificial intelligence (AI) has expanded ECG's risk-prediction potential, though its incremental value remains debated. This systematic review evaluated the predictive utility of conventional (non-AI) and AI/deep learning-enhanced ECG approaches for cardiovascular disease incidence, mortality, and major adverse cardiovascular events, comparing the two directly. The review followed PRISMA 2020 guidelines. Studies were identified through PubMed/MEDLINE, Scopus, Web of Science, and Google Scholar. Eligible studies were cohort studies, systematic reviews, or validated AI-based ECG investigations reporting risk estimates or predictive performance metrics. Findings were synthesized narratively and tabulated descriptively rather than statistically pooled. Thirty core studies were included across general, elderly, hypertensive, diabetic, and coronary artery disease cohorts. Conventional ECG abnormalities QT/QTc prolongation, QRS duration, left ventricular hypertrophy, ST-T abnormalities, and atrial fibrillation were consistently associated with cardiovascular disease, mortality, and MACE (hazard ratios generally 1.2–2.5). Adding ECG variables to conventional models yielded modest gains (ΔAUC ≈ 0.02–0.06); AI/deep learning models outperformed conventional interpretation (ΔAUC ≈ 0.10–0.15), including via ECG derived biological age. Conventional and AI-enhanced ECG correlates both carry meaningful, independent prognostic information.
No takes yet. Share an insight, caveat, or question.
Osarenkhoe et al. (2026) conducted a systematic review in Cardiovascular disease. AI/deep learning-enhanced and conventional ECG abnormalities vs. Conventional risk models or normal ECG interpretation was evaluated on Cardiovascular disease incidence, mortality, and major adverse cardiovascular events (MACE) (HR 1.2-2.5). AI/deep learning ECG models outperformed conventional ECG interpretation for predicting CVD, mortality, and major cardiovascular events.
Synapse has enriched 10 related papers. Consider them for comparative context: