Predicting Heart Diseases Using Enhanced Machine Learning Techniques

Abstract

According to recent surveys, cardiovascular disease is a leading global cause of death, resulting in a significant number of fatalities each year. In the field of medicine, data mining is gaining increasing recognition and significance. The medical industry generates a massiveand complex volume of data, making it challenging to handle and analyze using conventional approaches. Consequently, data mining emerges as a critical component to address this challenge. However, the accuracy of predictions is often questioned due to the high rate ofinaccuracy in some forecast computations. Therefore, selecting a prediction approach thatyields higher accuracy with fewer errors becomes crucial in this context. The objective of thisstudy is to develop a dependable system for forecasting heart illness. It is evident that the random forest algorithm consistently outperforms other methods in terms of precision. To further enhance the accuracy of the outcomes, the random forest method is subjected to hyper parameter tuning.