HEART FAILURE PREDICTION USING MACHINE LEARNING ALGORITHM

Abstract

Heart failure is a critical medical condition that occurs when the heart is unable to pump sufficient blood to meet the body's requirements. Early prediction of heart failure can significantly help in preventing severe complications and improving patient survival rates. This project aims to develop a machine learning model for predicting heart failure using patient medical data. The dataset used in this study contains 114 rows with key clinical features such as age, sex, cholesterol level, resting blood pressure, fasting blood sugar and electrocardiographic results. After data preprocessing and feature analysis, the Random Forest Classifier was implemented to predict the likelihood of heart failure. The model achieved an accuracy of 83%, indicating its effectiveness in identifying patients at risk. This study demonstrates how machine learning techniques can be applied in healthcare to assist clinicians in early diagnosis and better treatment planning.