A Machine Learning-Based Approach to Early Heart Disease Prediction with HeartSathi .

Abstract: Heart disease is one of the leading causes of mortality globally, often due to late diagnosis or lack of timely medical intervention. In this study, we present HeartSathi, a machine learning-based heart disease prediction model designed to assist healthcare providers in early diagnosis. By analyzing key clinical parameters such as age, blood pressure, cholesterol levels, heart rate, and other vital indicators, the system predicts the likelihood of a patient having a heart condition. The model leverages well-established algorithms including Logistic Regression, Random Forest, and Support Vector Machines (SVM) for accurate classification. Extensive testing was performed using public datasets such as the Cleveland Heart Disease dataset. Results show that HeartSathi can effectively predict heart disease risk with a high accuracy rate, thus demonstrating its potential as a supportive diagnostic tool for doctors and medical practitioners. This system contributes toward the broader goal of intelligent healthcare solutions aimed at improving patient outcomes and saving lives. Keywords: Heart Disease Prediction, Machine Learning, HeartSathi, Logistic Regression, Random Forest, SVM, Healthcare AI, Early Diagnosis, Medical Data Analysis, Predictive Modeling