Diabetes and heart disease are two common chronic conditions that require early diagnosis to prevent serious complications. At Yakrija Primary Clinic, the diagnostic process is still performed manually, often leading to inaccuracies and delays in decision-making. Therefore, an automated system is needed to improve diagnostic accuracy. This study aims to develop a classification model using the Support Vector Machine (SVM) algorithm to automatically diagnose patterns of diabetes and heart disease. The model is expected to enhance the accuracy and efficiency of the diagnostic process. This research employs the SVM method to classify patient data based on medical attributes such as Glucose, Blood Pressure, BMI, and age. The steps involved include data collection, pre-processing, normalization, training the SVM model, and evaluating model performance based on accuracy, precision, recall, and F1-Score using a Confusion Matrix. The developed SVM model showed an accuracy of 82.41% for diabetes, while for heart disease it achieved an accuracy of 95.24%. These results indicate an improvement in diagnostic accuracy compared to the manual method. Implementing the SVM model can provide significant enhancements in the accuracy and speed of diagnosing diabetes and heart disease. This model can be used as a support tool for medical decision-making, although further testing with more diverse data is necessary to improve generalization.