Diabetes Classification Using Machine Learning Techniques

Machine learning techniques play an increasingly prominent role in medical diagnosis. With the use of these techniques, patients’ data can be analyzed to find patterns or facts that are difficult explain, making diagnoses more reliable and convenient. The purpose this research was compare efficiency diabetic classification models using four machine techniques: decision trees, random forests, support vector machines, K-nearest neighbors. In addition, new proposed incorporate hyperparameter tuning addition some interaction terms into models. These were evaluated based on accuracy, precision, recall, F1-score. results study show with have better performance than those without for all techniques. Among terms, forest classifiers had best performance, 97.5% 97.4% 96.6% a 97% findings from further developed program effectively screen potential diabetes patients.