Improved Accuracy of Decision Tree with XGBoost Technique in Cat Skin Disease Diagnosis

This research aims to develop an expert system for initial diagnoses of skin diseases in cats using the Decision Tree method. It assists cat owners in identifying skin diseases based on observed symptoms. Data from expert veterinarian drh. Ismi Azima, including various types of cat skin diseases and their symptoms, were used. The research employs 80% training data and 20% testing data to develop the classification model. Testing results indicate the Decision Tree model achieves up to 90% average accuracy in diagnosing cat skin diseases based on 50 datasets. This expert system aids in diagnosis and provides treatment and prevention solutions, beneficial for cat owners, especially in areas with limited veterinary access. In conclusion, this Decision Tree-based expert system effectively provides initial diagnoses of skin diseases in cats with high accuracy.