چكيده به لاتين
Myocardial infarction (MI), also known as a heart attack, is the leading cause of death in the world. It often occurs due to the occlusion of coronary arteries, thereby leading to insufficient blood and oxygen supply that damage cardiac muscle cells. Because blood vessels are branching throughout the heart, MI occurs at different spatial locations (e.g., anterior and inferior portions) of the heart. Therefore, having corresponded to the electrical activity of the heart, the electrocardiogram (ECG) signals are being used for diagmosing MI. Most previous studies focused on the classification and early diagnosis of heart diseases. The objective of this study was to develop a novel change point detection method to monitor long-term acute MI treatment. A third-order tensor structure was employed to represent the 12-lead ECG data in three dimensions (beats × samples × leads). Exploiting intra-beat, inter-beat, and inter-lead correlations and channel variability of multi-lead ECG tensor, the weighted multivariate functional principal component analysis (WMFPCA) is incorporated into change-point models to construct monitoring statistics. Simulation results show that the proposed approach has fine performance in identifying change-points in various scenarios compared with some existing methods. Finally, by applying the suggested model on a real-world dataset, named PTB Diagnostic ECGdatabase, the model is verified.
