<![CDATA[Cats are among the most popular pets due to their friendly nature and relatively easy care, yet limited health attention often makes them vulnerable to skin diseases. Clinical examinations at veterinary clinics provide accurate results but require considerable time and cost. This study develops an early detection system for feline skin diseases, defined as a computational tool to help owners recognize symptoms at an early stage prior to advanced clinical diagnosis. The system integrates Dempster–Shafer Theory (DST) for disease classification and Fuzzy Type-2 for severity classification, where severity is categorized into mild, moderate, or severe based on symptom intensity. Fuzzy Type-2 was selected over type-1 fuzzy logic due to its superior ability to manage uncertainty and linguistic variability in veterinary assessments. The hybrid approach combines decision tree-based questioning with DST to identify the most probable disease, followed by Fuzzy Type-2 to evaluate severity. Validation was conducted using 100 medical records from the Easy Pet Care Animal Clinic in Tulungagung. For DST-based disease classification, evaluation with a confusion matrix on 100 cases achieved 83% accuracy, 93% precision, 86% recall, and an F1-score of 89%, demonstrating strong statistical performance. For severity prediction using fuzzy type-2, testing on 20 cases resulted in 85% correct classifications. These findings confirm that integrating DST with Fuzzy Type-2 provides an effective and statistically validated model for decision support in feline dermatology. The system offers a low-cost, fast, and reliable screening method that accelerates decision-making and minimizes delays in responding to potentially severe cases]]>
