Implicit Graph-Based Cardiovascular Disease Detection Using Cardiac Axis Deviation in Reduced-Lead ECG

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 graph <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$G=(V, E)$</tex-math></inline-formula> whose nodes <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$V=\lbrace \text{I}, \text{II}\rbrace$</tex-math></inline-formula> correspond to leads and whose edge weights <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$w_{ij}(t) \in E$</tex-math></inline-formula> capture time-varying cardiac axis deviation angles <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\theta (t)$</tex-math></inline-formula> in the frontal plane. Three statistical features are obtained mean angle <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\mu _\theta$</tex-math></inline-formula>, angular variance <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\sigma _\theta ^{2}$</tex-math></inline-formula>, and lead correlation coefficient <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\rho _{\text{I, II}}$</tex-math></inline-formula>. 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 with <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$O(1)$</tex-math></inline-formula> feature extraction complexity, providing an optimal trade-off between accuracy and computational efficiency for resource-constrained wearable ECG sensors and tele-ECG applications.