Dental and oral diseases are common health problems that require accurate diagnosis for appropriate treatment. Limited access to healthcare professionals highlights the need for a decision-support system that can assist in early diagnosis. This study aims to develop an expert system for diagnosing dental and oral diseases using a hybrid Certainty Factor (CF) and k-Nearest Neighbors (k-NN) method. CF is used to represent expert knowledge through rules with confidence values, while k-NN classifies diseases based on the similarity of case data. The dataset was constructed from dental and oral disease symptoms represented as binary data. System performance was evaluated using a confusion matrix, precision, recall, F1-score, and k-fold cross-validation. The results show that the hybrid method achieved an accuracy of 88%, outperforming CF at 78% and k-NN at 82%. The evaluation also indicates that the hybrid method provides more stable performance and improves diagnostic quality. Therefore, the developed expert system can provide more accurate diagnostic results and serve as a supporting tool for the early detection of dental and oral diseases.
Copyrights © 2026