Abstract
Heart disease is the major global cause of death in the modern era. Heart illness might be difficult to diagnose. It requires a number of expensive diagnostic tests to be found. The scientific community is undergoing a transformation thanks to machine learning (ML), a subset of artificial intelligence. In this paper, exploratory data analysis (EDA) utilizing multivariate analysis is utilized to find correlations and outliers in the data. The study's dataset consists of 270 records with 14 variables, including age, chest pain type, blood pressure, blood glucose level, resting ECG, heart rate, and chest pain. Logistic Regression algorithm is employed on the dataset to predict heart disease on the basis of chosen risk factors that are obtained using recursive feature elimination incorporating random forest classifier method. The paper entails pre-processing methods, proposed algorithms, evaluation metrics and an accurate prediction based on the methodology.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
