Heart Disease Prediction Using Logistic Regression

Abstract

This study presents a heart disease prediction system leveraging logistic regression. The process begins with preprocessing patient records by handling missing data, scaling features, and splitting datasets. Relevant input attributes such as cholesterol levels are utilized for model training and optimisation. The logistic regression model predicts the probability of heart disease based on input features. The system's output includes disease classification and is assessed using key performance metrics. This approach aims to enhance early detection and clinical decision- making efficiency.