Machine learning Approach for Detection of Cardiovascular Disease: A Comprehensive Review

Abstract

One of the major problems facing the globe today is heart sickness, which is also one of the main killers in many countries. Electrocardiogram (ECG) and patient data can be used to detect cardiac illness in early stages, as shown by recent advancements in machine learning (ML) application. Machine learning is becoming more precise and accurate in its classification of clinical cardiac disease datasets in recent years. Early heart disease identification is a major issue for healthcare services (HCS). This study offers a quick overview of countless machine learning techniques for detecting heart sickness. This research examines the use of machine learning methods to identify cardiac disease. Five methods were examined to assess how well they could identify cardiac illness, including “SVM (Support Vector Machine), RF (Random Forest), DT (Decision Tree), KNN (K-Nearest Neighbors), and NB (Naïve Bayes).  Among all the ML technique, we found out the best with respect to Accuracy is SVM (which gives the highest average accuracy of 96.19%).Additionally, this review paper provides a valuable resource for researchers and field worker, as it eliminates the need to study all 48 papers individually .By reading our paper, they can efficiently grasp the key insight and gain a solid understanding of the examined technique of the without the burden of reviewing each individual study.