Authors: Kurt, B., & Buçan Kırkbir, İ.
Citation: Eskişehir Technical University Journal of Science and Technology A – Applied Sciences and Engineering, 24(2), 107–120.
DOI: https://doi.org/10.18038/estubtda.1025092
Summary: This study developed a machine learning–based clinical decision support system to assist physicians in the early diagnosis of myocardial infarction. Among several models tested (Decision Tree, SVM, ANN, Probit Regression), the ANN model achieved 98% sensitivity and 93.7% specificity using optimized clinical and biochemical variables. The system supports precision cardiology by enabling faster and more accurate identification of heart attack risk, directly contributing to AI-driven approaches in vascular disease management.
