<![CDATA[This study aims to design and develop an expert system for diagnosing Diabetes Mellitus using the Bayes Theorem method. The system was created to help users identify their level of diabetes risk based on 21 symptoms commonly found in patients. The research was conducted as a case study at Imbi Community Health Center, a healthcare facility in Jayapura City that has not yet implemented a probabilistic-based diagnostic support system. This condition causes the early detection process of diabetes to rely solely on manual examinations by medical personnel, which requires more time and may lead to inaccuracies during the initial diagnostic stage. Bayes Theorem was chosen because it is capable of handling uncertain data and producing probabilities that represent the likelihood of each type of diabetes, namely Type 1 Diabetes Mellitus, Type 2 Diabetes Mellitus, and Gestational Diabetes. The test results show that the system can calculate the posterior probability for each disease type based on the symptoms selected by the user, and then classify the diagnostic outcome into three categories: No Diabetes, Possible Diabetes, and Confirmed Diabetes. The system also provides the final diagnostic conclusion by selecting the highest probability obtained from the calculations. With the implementation of this system at Imbi Community Health Center, both medical personnel and the community can perform early detection more quickly and systematically before undergoing further clinical examinations. This study serves as a foundation for developing more accurate and comprehensive expert systems in the future, including integration with clinical data, the development of web- or mobile-based interfaces, and the application of other artificial intelligence methods in subsequent research.]]>
