This report covers introduction to data classification using classification algorithm on medical field dataset i.e., Pima Indian Diabetes Dataset. The essential goal of this paper is to investigate the Data Science interaction to indicatively anticipate regardless of whether the patient has diabetic side effects in light of a few demonstrative estimations like age, BMI, insulin level, number of pregnancies and so on. In this study, the KNN approach is used as the foundation for illness prediction. Here the implement indicate classification algorithm that outperforms previous algorithms in terms of correctly identifying whether the patient is in-care or out-care. The algorithm merge as hybrid to provides better results and can further improve the decision-making process in hospitals and other medical care units.