Heart Disease Detection Using Machine Learning: Design, Implementation and Performance Analysis

The Cardio Guard system successfully implements machine learning for heart disease risk prediction through a full-stack web application. Multiple algorithms were trained and evaluated, with the Random Forest model achieving the highest accuracy and being selected for deployment. The system integrates a Flask backend, responsive frontend, and SQLite database to provide real-time prediction, classification into high-risk and low-risk categories, and downloadable PDF reports, along with prediction history and role-based access for patients, doctors, and administrators. Practically, the system serves as an effective preliminary screening tool for early detection of heart disease and assists users and healthcare professionals in making informed decisions, demonstrating the real-world applicability of machine learning in healthcare.

[1]   J. Smith, A. Brown, “Machine Learning-Based Heart Disease Prediction Using Ensemble Methods,” IEEE Access, vol. 13, pp. 10234–10245, 2025. [2]   R. Verma, S. Kulkarni, “Explainable AI for Cardiovascular Risk Prediction Using Hybrid Models,” Springer Healthcare Informatics, 2025. [3]  L. Chen, Y. Zhao, “Advanced Random Forest Optimization for Medical Diagnosis Systems,” Elsevier Journal of Biomedical Informatics, 2025. [4]    P. Sharma, K. Singh, “Web-Based Healthcare Systems Using Machine Learning and Flask Framework,” International Journal of Computer Applications, 2025. [5]   M. Gupta, R. Shah, “Comparative Analysis of Machine Learning Algorithms for Heart Disease Detection,” IEEE Xplore, 2025. [6]  A. Khan, M. Ali, “Heart Disease Prediction Using Supervised Learning Techniques,” Journal of Healthcare Engineering, 2024. [7]   S. Patel, D. Mehta, “Integration of Machine Learning Models in Web Applications for Disease Prediction,” Springer, 2024. [8]   Y. Li, X. Wang, “Performance Evaluation of SVM and Random Forest in Medical Data Classification,” Elsevier, 2024. [9]  N. Gupta, P. Agarwal, “Flask-Based Web Systems for Real-Time Healthcare Prediction,” International Journal of Advanced Research in Computer Science, 2024. [10]  T. Roy, A. Das, “Data Preprocessing Techniques for Improving ML Model Accuracy in Healthcare,” IEEE Access, 2024.