Performance Analysis of Machine Learning Classification Algorithms in the Case of Heart Failure Prediction

Machine Learning is one of the most rapidly developing technologies, and it is currently being utilized in every kind of application. The Healthcare industry has been benefiting exponentially from this emerging technology. Among the number of advantages heart failure prediction is one of them. Almost 17.9 million people die from heart disease every year. This research predicts heart failure with seven machine learning classification algorithms by the factors or features of health conditions such as age, resting blood pressure, chest pain type, cholesterol, fasting blood sugar, resting electro diagram, maximum heart rate, etc. Then, it is accompanied by a comparative performance analysis of these algorithms. The research shows that Naive-bias, Random Forest, and Support Vector Machines are outperformed to predict heart failure. The accuracy of these algorithms is almost 85-86%.