A Comprehensive Review of Heart Disease Classification Techniques Utilizing ECG Signal Analysis

Heart disease(HD), poses a global threat to human life. Despite its utmost significance, finding solutions for this issue remains challenging. One effective approach is the early and accurate identification of abnormal cardiac signals, which plays a vital role in diagnosing heart problems and preventing catastrophic outcomes. Healthcare professionals employ the Electrocardiogram (ECG) as a tool to evaluate heart-related electrical activity. By carefully analyzing ECG patterns, they can anticipate conditions like arrhythmia and congestive heart failure. This paper presents an in-depth review of cutting-edge techniques employed in ECG-based heart disease classification, meticulously evaluating the performance of various classification algorithms, including support vector machines, random forests, neural networks, and ensemble methods, in effectively identifying heart diseases from ECG data, this study aspires to serve as an indispensable resource for researchers, clinicians, and healthcare professionals alike. Through its comprehensive overview, the review strives to engender a profound understanding of the current state-of-the-art techniques, elucidating their inherent strengths, and limitations, and also explores the potential of ensemble learning methods for enhancing classification accuracy through model combination. These findings contribute to a better understanding of different models.