Interpretable AI in cardiology: a real-world study on myocarditis and acute coronary syndrome

Official URL: https://dx.doi.org/10.1109/SIU66497.2025.11112008

Machine learning models have the potential to play a significant role in the diagnosis of cardiovascular diseases. However, for these models to be clinically reliable, they must be explainable. In this study, various machine learning algorithms were applied to distinguish between myocarditis and acute coronary syndrome (ACS), and the explainability of these models was evaluated. Logistic Regression, Support Vector Machines, and Random Forest models were trained using data obtained from Turkey's largest cardiology hospital. The obtained results were analyzed through global feature importance and SHAP values to explain the decision mechanisms of the models. The study aims to enhance physicians' trust in AI-based systems by illustrating how Explainable Artificial Intelligence (XAI) techniques can be applied in medical diagnosis settings.