Short-term Repeatability of Artificial Intelligence Estimated Electrocardiographic Age

Advancements in artificial intelligence have enabled estimation of cardiac age from raw ECG waveforms. ECG-age is a novel metric that provides insights into cardiac function and has shown potential for CVD risk prediction. However, its short-term repeatability remains unclear. ECG-age was measured in 58 participants across two visits, one to two weeks apart. The intraclass correlation coefficient was 0.64 (95% CI: 0.52, 0.76), with a standard error of measurement of 2.6 years. Findings suggest moderate short-term repeatability, with notable within-visit variation. Refining AI algorithms is essential to establish ECG-age as a reliable biomarker for CVD risk assessment and clinical decision-making.