Performance evaluation of machine learning techniques for heart disease prediction: An overview

One of the most common and serious diseases is heart disease, as it is one of the major causes of death globally. Heart disorders come in many forms, including arrhythmia, congenital heart disease, and atherosclerosis. Patients with heart disease experience a variety of symptoms, such as dizziness, chest discomfort, and excessive perspiration. Heart disease is primarily caused by smoking, high blood pressure, diabetes, obesity, and other risk factors. Developing an affordable and non-invasive approach to predicting heart disease is necessary. Creating a system that accurately predicts heart disease with minimal errors is essential. Consequently, machine learning is vital for predicting the risk of future cardiopathy by analysing the patient's health conditions and past medical history to decrease the possibility of mortality from heart disease. Machine learning (ML) has rapidly advanced in recent years, and its application in medical sciences can revolutionize how complex diagnostic and prognostic evaluations are conducted at the individual patient level. ML helps predict the risk of developing heart disease based on the patient's current and historical medical conditions to decrease the chances of death due to heart disease. ML techniques, including Random Forest, ANN, Linear Regression (LR), Logistic Regression (LR), K-Nearest Neighbor (KNN), Naive Bayes (NB), Support Vector Machine (SVM), Gradient Boosting, and Decision Tree (DT), are utilized to create the machine learning model. This paper presents an overview of the Heart Disease Prediction system using Machine Learning techniques. A detailed tabular comparison of the reviewed papers is also included.