Penelitian ini bertujuan untuk membangun dan membandingkan model machine learning menggunakan Support Vector Machine (SVM) dan Naive Bayes (NB) untuk diagnosis Diabetes Melitus di Puskesmas Petarukan, Kab. Pemalang, Jawa Tengah. Variabel yang digunakan mencakup umur pasien, kadar gula darah sewaktu (GDS), kadar gula darah puasa (GDP), dan kadar HbA1c. Pra-pemrosesan data meliputi penanganan outlier, normalisasi, dan pembagian data. Evaluasi model dilakukan menggunakan confusion matrix untuk melihat akurasi, presisi, recall, dan F1-score. Hasil penelitian menunjukkan bahwa model Naive Bayes memiliki kinerja terbaik dengan akurasi 89,6%, presisi 88%, recall 94,3%, dan F1-score 0,91. Normalisasi data meningkatkan kinerja SVM, sedangkan Naive Bayes tidak terpengaruh secara signifikan.

This study aims to build and compare machine learning models using Support Vector Machine (SVM) and Naive Bayes (NB) for the diagnosis of Diabetes Mellitus at the Petarukan Health Center, Pemalang Regency, Central Java. The variables used included the patient's age, current blood sugar level (GDS), fasting blood sugar level (GDP), and HbA1c level. Data pre-processing includes outlier handling, normalization, and data sharing. Model evaluation was carried out using a confusion matrix to see accuracy, precision, recall, and F1-score. The results show that the Naive Bayes model has the best performance with 89.6% accuracy, 88% precision, 94.3% recall, and an F1-score of 0.91. Data normalization improved the performance of SVM, while Naive Bayes was not significantly affected.