• Harshada Manohar Trimukhe
• Shyam Sundar Tiwari
• Ritik Sonaji Wandale
• Rohit Pralhad Warade
• Shailesh Galande

Predictive models for heart disease are essential for early identification and treatment. By using an extra feature—a health percentage assessment that classifies cardiac condition status as good, moderate, or bad—this study improves on previous methodologies. We assess the performance of Support Vector Machine (SVM) and Decision Tree algorithms using clinical variables collected from people with and without heart disease. These attributes include age, blood pressure, cholesterol levels, and exercise habits. Accuracy, precision, recall, and F1-score are among the evaluation criteria, and robustness is guaranteed by methods like cross-validation and hyperparameter adjustment. Findings show that both SVM and Decision Tree models perform well, and they also provide information on how accurate and computationally efficient they are. By adding the health percentage evaluation, these models become more predictive, which helps researchers and clinicians make better judgments about the diagnosis, treatment, and prognosis of heart disease.

Machine learning, SVM, decision tree, risk analysis

"Leveraging Machine Learning for a Heart Health Analysis and Prediction System ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.i534-i538, April-2024, Available :http://www.jetir.org/papers/JETIR2404870.pdf

"Leveraging Machine Learning for a Heart Health Analysis and Prediction System ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppi534-i538, April-2024, Available at : http://www.jetir.org/papers/JETIR2404870.pdf