Spectral Method And Machine Learning-Based Multi-Classification Of Myocardial Infarction Cardiac Diseases

Abstract

Myocardial Infarction (MI) Remains One Of The Leading Causes Of Cardiac-Related Mortality Globally, Posing A Significant Burden On Public Health Systems, Including In Ethiopia. Early And Accurate Diagnosis Is Crucial For The Effective Management And Treatment Of MI And Its Various Subtypes. Electrocardiogram (ECG) Serves As A Primary, Non-Invasive Diagnostic Tool Due To Its Capacity To Reveal Critical Cardiac Anomalies, Particularly Through Analysis Of The QRS Complex. However, Reliable Interpretation Of ECG Signals Is Challenged By Artifacts Such As Baseline Wander, Motion Interference, And Muscle Contraction Noise. This Research Presents A Comprehensive Diagnostic Framework That Integrates Advanced Spectral Analysis And Machine Learning Techniques For Multi-Classification Of Myocardial Infarction. The Study Explores Four Major Spectral Techniques, Stationary Wavelet Transform (SWT), Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), And Stockwell Transform (ST), To Decompose ECG Signals Into Relevant Time-Frequency Domains. From These Decomposed Spectral Bands, Nonlinear Entropy-Based Features Such As Sample Entropy And Bubble Entropy Are Extracted To Capture The Inherent Complexity And Irregularities Within The MI Signal Dynamics. These Features Are Then Employed To Train Multiple Machine Learning Classifiers Including Random Forest (RF), Bayesian Optimized Support Vector Machine (BOSVM), Adaptive K-Nearest Neighbours (AKNN), SVM (Support Vector Machine), Adaboost, Decision Tree (DT), And Extreme Learning Machine (ELM). The Simulation Results Indicated That The Combined Spectral And Nonlinear Approach, With Performance Metrics Ranging From 90 ?�? 99.96% For Most Of The Classes, Significantly Outperformed The Individual Spectral And Nonlinear Methods That Ranged From 71 - 89.9% For Some Of The Classes. Among The Combined Approaches, The DWT-Based BOSVM Model Achieved An Accuracy Of 99.94%, Specificity Of 99.96%, Sensitivity Of 99.85%, Precision Of 99.86%, And F1-Score Of 99.85%. This Robust Model Shows Great Promise For Real-Time Implementation In Clinical Diagnostic Systems.