AI-Powered Early Diagnosis and Personalized Health Recommendations for Coronary Artery Disease (CAD) using Predictive Analytics
Cardiovascular disorders, particularly coronary artery disease, are the predominant cause of mortality globally. Consequently, the urgent necessity for early detection and individualized treatment techniques for coronary artery disease (CAD) has intensified. This research proposes an AI-driven system utilizing machine learning techniques for the prompt diagnosis of CAD risk based on 13 clinical factors. The system employs an ensemble learning approach incorporating logistic regression, random forest, and support vector machine classifiers to enhance prediction accuracy. The suggested system includes an AI chemist assistant that assists users with medication-related inquiries, including drug interactions, administration guidelines, and prescription clarifications. This tool utilized Google's generative AI (Gemini) to process verbal and visual inputs, enabling users to upload images or pose inquiries for immediate support. The system includes a health recommendation engine that suggests lifestyle modifications based on risk assessments, as well as a chatbot that addresses general inquiries regarding diet, exercise, sleep, or any symptoms experienced by the user. This method offers a comprehensive preventative care solution by integrating CAD risk prediction, AI-driven pharmaceutical support, a coronary health chatbot, and lifestyle guidance. In addition to enhancing accessibility, the proposed solution also advances patient education and facilitates more informed decision making in the management of cardiovascular disease. The experimental findings demonstrate the efficacy of the ensemble model in predicting CAD risk and the AI chemist's ability to assist users with medication-related inquiries. This integrated system seeks to amalgamate AI-driven diagnostic methods with therapeutic and general cardiovascular health support, thereby enhancing the efficacy and accessibility of healthcare services.
Authors
- Siddharth Vats (ORCID: https://orcid.org/0000-0002-4225-651X)
- Khema R. Sharma
- M. Revathi (ORCID: https://orcid.org/0000-0002-4996-3292)
Institutions
- SRM Institute of Science and Technology (IN)
- Institute of Computing Technology (CN)
Publication Details
- Published
- 2025-07-04
- DOI
- https://doi.org/10.1109/icctdc64446.2025.11158896
- Primary Topic
- Artificial Intelligence in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00