Electrocardiographic Signatures of Dysglycaemia: Mechanistic Foundations, Digital Biomarkers, and Artificial Intelligence for Non-Invasive Diabetes Risk Stratification

Diabetes mellitus is projected to affect more than 1.3 billion people worldwide by 2050, with millions remaining undiagnosed or in a prediabetic state. Cardiovascular complications account for nearly half of diabetes-related deaths, highlighting the need for scalable tools capable of identifying metabolic dysregulation before irreversible cardiac damage develops. This review synthesizes current mechanistic, clinical, and computational evidence linking diabetes to cardiac electrophysiological remodeling and examines electrocardiography (ECG) as a non-invasive modality for early detection of dysglycaemia. Chronic hyperglycaemia, insulin resistance, oxidative stress, microvascular dysfunction, and cardiac autonomic neuropathy collectively contribute to measurable ECG alterations, including QT/QTc prolongation, increased QT dispersion, changes in Tp–e indices, and reduced heart rate variability. These changes often precede overt cardiovascular disease and correlate with glycaemic burden and diabetes duration. Recent advances in signal processing and artificial intelligence have expanded the diagnostic potential of ECG. Both classical machine learning approaches and large-scale deep learning models demonstrate that ECG contains latent signatures associated with incident type 2 diabetes and glycaemic status. Despite promising results, heterogeneity in study design, limited representation of prediabetes, and lack of standardized validation frameworks remain major barriers to clinical translation. Prospective, multi-ethnic studies are needed to establish ECG-based screening as a reliable component of early diabetes detection strategies.