Perancangan Sistem Pakar Prediksi Diagnosis Penyakit Diabetes Menggunakan Algoritma Naive Bayes Berbasis Web

Diabetes mellitus is a metabolic disease with increasing prevalence worldwide, including in Indonesia. Early detection and accurate diagnosis are crucial to prevent serious complications. This research aims to design a web-based expert system using the Naive Bayes algorithm to predict the diagnosis of diabetes. The Naive Bayes algorithm was chosen for its ability to process data quickly and produce accurate predictions despite its simple assumptions. The research method used is the Waterfall method, which includes the stages of analysis, design, coding, testing, implementation, and maintenance. This system is designed to assist the public in detecting the risk of diabetes based on entered symptoms and medical data. The evaluation results of the expert system for diagnosing diabetes by applying the Naive Bayes algorithm through testing on 35 patient datasets showed results consistent with the level of expertise obtained from whitebox and blackbox system testing. This system is expected to be an effective tool for medical professionals and the general public in making early diagnoses of diabetes. The conclusion of this research is that a Naive Bayes-based expert system can provide accurate and fast predictions, thereby improving the quality of healthcare services.