Analysis of Diabetic Prediction Using Machine Learning Algorithms on BRFSS Dataset

Due to the detrimental effects it has on everyone's health, diabetes is a chronic condition that still poses a serious threat to the global population. It is a metabolic disorder that increases blood sugar levels and increasing the risk of heart disease, kidney failure, stroke, issues with the nerves and heart, among other issues. Over the years, several scholars have sought to create reliable diabetes prediction models. Due to a lack of adequate data sets and prediction techniques, this discipline still faces many unsolved research issues, which forces researchers to apply big data analytics and ML-based methodology. The paper investigates healthcare prediction analytics and addresses the issues using four different machine learning methods. This study has utilized the Early detection and Binary 012 databases. Based on these datasets, the precision, recall, and accuracy of KNNs and Random Forest methods are calculated. The study's findings may be valuable to health professionals, stakeholders, students, and researchers engaged in diabetes prediction research and development because SVM performs better than KNN and Logistic Regression.