A novel graph-based approach using only leads I and II can detect cardiovascular disease with high accuracy, offering a computationally efficient solution for wearable and tele-ECG applications.
Accurate and effective cardiovascular disease (CVD) diagnosis is particularly difficult in telemedicine and resource-constrained environments due to traditional multi-lead ECG devices' high computational and operational expenses. We propose a computationally effective graph-based approach to the automated detection of CVD from reduced-lead I, II electrocardiogram. The approach formulates lead relationships as a dynamic graphG= (V, E) whose nodesV= I, IIcorrespond to leads and whose edge weightsw₈₉ (t) Ecapture time-varying cardiac axis deviation angles (t) in the frontal plane. Three statistical features are obtained mean angle _, angular variance _ ^2, and lead correlation coefficient ₈, ₈₈. Experimental testing on PTB-XL and PTB datasets establishes state-of-the-art performance at 89. 2% and 84. 1% accuracy, respectively, without redundant computations native to multi-lead ECG. The approach ensures clinical-grade accuracy withO (1) feature extraction complexity, providing an optimal trade-off between accuracy and computational efficiency for resource-constrained wearable ECG sensors and tele-ECG applications.
Jaiswal et al. (Wed,) studied this question.