Interpretable AI in Cardiology: A Real-World Study on Myocarditis and Acute Coronary Syndrome Kardiyolojide A iklanabilir Yapay Zeka: Miyokardit ve Akut Koroner Sendrom zerine Ger ek D nya ali smasi
33rd IEEE Conference on Signal Processing and Communications Applications, SIU 2025, İstanbul, Türkiye, 25 - 28 Haziran 2025, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/siu66497.2025.11112008
- Basıldığı Şehir: İstanbul
- Basıldığı Ülke: Türkiye
- Anahtar Kelimeler: Machine Learning, Explainable Artificial Intelligence, Cardiology, Myocarditis, Acute Coronary Syndrome
- Sağlık Bilimleri Üniversitesi Adresli: Evet
Özet
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.