부산대학교 도서관

Through the use of machine learning models, particularly Random Forest and Support Vector Machines, this work increases the prediction of CHD risk as well as achieves a remarkably high predictive accuracy. The use of interpretability methodologies clarifies important aspects of CHD risk estimation, stressing the importance of elements like age, cholesterol levels, as well as smoking behavior. Additionally, the creation of a user-friendly application streamlines the risk assessment procedure and improves communication between healthcare professionals and patients. Future studies need to focus on prospective validation, data source diversity, and ethical issues to better advance the subject. CHD risk management has a bright future thanks to the possible integration of real-time patient data and the advancement of AI-driven decision support systems.