Akademik Veri Yönetim Sistemi
SIGNAL IMAGE AND VIDEO PROCESSING, cilt.19, sa.4, 2025 (SCI-Expanded, Scopus)
Acute Myocardial Infarction (AMI) remains a major health problem globally despite advances in diagnosis and treatment. Although electrocardiography (ECG) is a popular diagnostic tool, it can be difficult to interpret due to signal variability and pathology-related changes. This study proposes a triple approach to classify Healthy Controls (HC), ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI) by applying the triple method to 12-lead ECG signals. The proposed method includes automatic feature and ECG derivation selection using Particle Swarm Optimisation (PSO), Least Absolute Shrinkage and Selection Operator (LASSO) and Linear Regression (LR) and signal decomposition using Variational Mode Decomposition (VMD). Classification is performed using machine learning algorithms such as Artificial Neural Network (ANN), K-nearest neighbours (KNN), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). The proposed method is evaluated using both the original clinical dataset and the PTB-XL database. As a result of the evaluation, high classification performance was achieved for both the clinical dataset (Accuracy: 100%) and the open-source PTB-XL dataset (Accuracy: 99.60%). The results obtained in this study demonstrate the potential for fast and reliable diagnosis. The proposed work contributes to addressing the challenge of distinguishing between STEMI and NSTEMI, which is crucial for the treatment of AMI patients.