Rule-Based Expert System Model with Backward Chaining Algorithm for Symptom-Based Skin Disease Diagnosis

A rule-based expert system was a computational model designed to emulate expert decision-making using a knowledge base and inference algorithms. This research developed a rule-based expert system model with a backward chaining algorithm to diagnose skin diseases based on clinical symptoms. Backward chaining, a goal-driven inference method, started with a disease hypothesis (e.g., psoriasis) and verified related symptoms (e.g., kemerahan, sisik keperakan), enabling efficient differentiation of skin diseases with overlapping symptoms, such as dermatitis, psoriasis, and scabies. The model provided advantages in handling uncertainty, produced accurate diagnoses, and supporting interactive symptom verification. Developed using a knowledge base from credible sources like WHO and AAD, the model was intended to assist in clinical decision-making. The results showed that the backward chaining algorithm effectively improved the accuracy and efficiency of diagnosing skin diseases based on patient-reported symptoms