Makine Öğrenimi Yöntemlerini Kullanarak Salgın Hastalık Şiddetinin ve Salgın Hastalık Faktörlerinin Göreceli Önemlerinin Tahmin Edilmesi

Epidemic diseases have been seen frequently in recent years. Today’s, thanks to advanced database systems, it is possible reach the clinical and demographic data of citizens. With help these data, machine learning algorithms can predict how severe (at home, hospital or intensive care unit) disease will be experienced by patients risk group before epidemic begins spread. estimates, necessary precautions taken. In this study, during COVID-19 epidemic, obtained from Italian national drug was used. severity features (Age, Diabetes, Hypertension etc.) that affect estimated using mining (CRISP-DM method), approaches (Bagged Trees, XGBoost, Random Forest, SVM) an algorithm solving unbalanced class problem (SMOTE). According experimental findings, Bagged Classification Regression Trees CART) yielded higher accuracy prediction results than other methods (83.7%). Age, cardiovascular diseases, hypertension, diabetes were four highest significant based on relative calculated CART classifier. The proposed method implemented without losing time different may arise future.