Diabetes is a chronic disease affecting millions of people worldwide and requires early diagnosis to prevent serious health complications. Machine learning techniques have recently been applied to healthcare data to assist in disease prediction and risk analysis. This research proposes a diabetes prediction system using synthetic medical data and a machine learning classification model. A dataset containing health-related attributes such as glucose level, body mass index (BMI), age, blood pressure, skin thickness, insulin level, number of pregnancies, and diabetes pedigree function was generated using the scikit-learn synthetic data generator. A Random Forest classification model was trained to predict whether a patient is diabetic or non-diabetic. Model performance was evaluated using metrics such as accuracy, confusion matrix, classification report, and ROC-AUC score. Experimental results demonstrate that the proposed model achieves high prediction accuracy and can assist healthcare systems in identifying individuals at risk of diabetes.
