Diabetes, or Diabetes Mellitus, stands as a prevalent chronic ailment with a global reach, affecting numerous individuals across the world. It involves elevated levels of blood sugar, posing potential serious consequences for various organs in the human body. Persistently high blood sugar levels in individuals with diabetes can result in metabolic imbalances, paving the way for a cascade of complications like coronary disorder, neuropathy, retinopathy. Detecting diabetes in its early stages is crucial, as prompt intervention can avert the onset of severe complications. Many researchers in the past have delved deeply into the realm of utilizing machine learning algorithms for predicting diabetes. In this work various machine learning methods, including Logistic Regression (LR), Support Vector Classifier (SVC), and Decision Tree (DT) and Random Forest (RF), Adaptive Boosting (AB) and Gradient Boosting (GB) have been applied to identify diabetic patients using publicly available Kaggle dataset. AdaBoost achieved an impressive overall accuracy of 97.22%, while Gradient Boosting demonstrated a slightly superior performance with an overall accuracy of 97.24%.