COMPARATIVE ANALYSIS OF LOGISTIC REGRESSION, SUPPORT VECTOR MACHINE AND RANDOM FOREST ALGORITHMS FOR HEART DISEASE PREDICTION

The Comparative Analysis of Logistic Regression, Random Forest, and SVM for Heart Disease Prediction System focuses on evaluating and implementing machine learning models to assess the risk of heart disease based on user provided health data. This system not only predicts the likelihood of heart disease but also compares the performance of three widely used algorithms as Logistic Regression, Random Forest, and SVM to determine their efficacy in this domain. The system begins with users entering essential health metrics, such as age, gender, blood pressure, cholesterol levels, chest pain type, and other medical factors, through an intuitive web interface. The input data undergoes preprocessing, including cleaning, normalization to ensure the accuracy and reliability of predictions. Each of the three machine learning models is then applied to the processed data, and their predictions are compared using performance metrics like accuracy, precision, recall, F1-score, ROC curves. By implementing this comparative approach, the system not only delivers predictions but also highlights the strengths and weaknesses of each model in handling heart disease datasets. The results of the comparative analysis are visually presented, helping users and stakeholders understand the model performances and their suitability for such critical healthcare applications. The project bridges the gap between machine learning and healthcare by not only providing actionable insights to users but also contributing to the ongoing research on machine learning algorithms in healthcare. By facilitating early detection and intervention, the system supports improved healthcare outcomes while showcasing the comparative effectiveness of different machine learning techniques for heart disease prediction.