Phys Eng Sci Med. 2026 Jul 14. doi: 10.1007/s13246-026-01760-0. Online ahead of print.
ABSTRACT
Globally, cardiovascular diseases (CVDs) constitute a leading cause of death. Significant reductions in mortality are possible with early detection and treatment of CVDs. The electrocardiogram (ECG) is an easy-to-understand, non-invasive technique for assessing the state of the heart. A specific CVD can be determined by a slight deviation in the ECG, which is difficult and time-consuming to diagnose manually. This work suggests an empirical mode decomposition (EMD)-based approach together with time and frequency series feature extraction for the automated identification of CVDs. Five CVDs are taken into consideration in this work: myocardial infarction (MI), hypertrophic cardiomyopathy (HCM), dilated cardiomyopathy (DCM), bundle branch block (BBB) and coronary artery disease (CAD). The decomposition of signals using EMD yields amplitude- and frequency-modulated waves called intrinsic mode functions (IMFs). Temporal and spectral features are extracted from the obtained IMFs. These features are ranked using the one-way anova test, and the ranked features are fed as inputs to the classification model. When combined with eleven features, the extreme gradient boosting classifier allows the suggested approach to attain a maximum classification accuracy of 99.56%. On the proposed database and 92.4% on MIT-BIH database, demonstrating strong generalizability. Clinical validation on 6,55,659 beats from RELA Hospital yielded 81.3% accuracy, highlighting the challenges of real-world deployment.
PMID:42446844 | DOI:10.1007/s13246-026-01760-0
