Comparing Fuzzy Logic Mamdani and Naïve Bayes for Dental Disease Detection

Background: Dental disease detection is essential for the diagnosis of dental diseases. Objective: This research compares Mamdani fuzzy logic and Naïve Bayes in detecting Methods: The first to process data on symptoms support tissues based complaints toothache consulted with experts at a community health centre (puskesmas). second apply proposed expert system. third provide recommended decisions about diseases symptom inputted into Patient were collected North Cilacap puskesmas between July December 2021. Results: converts uncertain values definite values, method classifies type by calculating weight patients’ answers. methods tested 67 patients complaints. accuracy rate was 85.1%, 82.1%. Conclusion: prediction compared diagnoses determine whether better than method. Keywords: Disease, Expert System, Fuzzy Logic, Bayes, Prediction