AI-enabled clinically aligned fewer-lead ECG approaches for detecting cardiovascular diseases

Abstract The 12-lead electrocardiogram (ECG) is the clinical gold standard for cardiovascular disease (CVD) detection, though its use in self-care and resource-limited settings is constrained by complex configurations and reliance on specialised diagnostic infrastructure. Commercially available portable/wearable artificial intelligence-enabled ECGs (AI-ECGs) using fewer leads offer greater accessibility yet face clinical integration challenges due to misalignment with gold standard lead configurations, and restricted detection capabilities and clinical interpretability. Consequently, recent research emphasises development of clinically aligned fewer-lead AI-ECG approaches, where the leads are aligned with the 12-lead ECG and used individually or in combinations. However, these approaches remain largely pre-commercial, and comprehensive evaluation is needed to determine their potential and limitations for clinical and self-care acceptability. This review critically assesses 316 studies in terms of detected CVD types, selected leads and rationale for lead selection, and diagnostic performance of AI methods. Key findings reveal limitations in detectable CVD types, diagnostic consistency, incorporation of cardiac electrophysiology and lead interdependency insights, along with the limited adoption of advanced multi-task learning, adaptive methods and explainable AI models. This review also outlines future directions to develop compact and clinically aligned fewer-lead AI-ECGs, bridging the gap between innovation and practical application in clinical and self-care settings.