Comparative Analysis of Machine Learning Algorithms for Heart Disease Predictions
Sanjay Patidar, Anvay Jain, Ayush Gupta
Abstract
The number one reason of deaths worldwide are cardiovascular diseases. An approximate of 17.9 million lives die because of CVDs every year, which means it is responsible for 31% of all deaths globally. Four out of five CVD deaths are because of heart assaults and strokes, and one-third of these deaths arise upfront in humans below 70 years of age. Heart failure is a not unusual occasion due to CVDs and this dataset consists of eleven functions that can be used to expect a probable heart sickness. This research work has used three different Machine Learning [ML] classifier models such as Logistic Regression Classifier, K-Nearest Neighbors Classifier, and Random Forest Classifier. These three Machine Learning models are then compared based on a five-evaluation metrics to find out the best suited model for disease detection.