Type 2 Diabetes Prediction using K-Nearest Neighbor Algorithm

Type 2 diabetes is a persistent disorder that affects millions of individuals globally. It characterised by the excessive levels glucose within blood due to insulin resistance or incapability supply insulin. Early detection and prediction type can improve patient outcomes. K-Nearest Neighbor (KNN) used in present model predict diabetes. The KNN set rules simple but powerful machine learning for categorization regression. It's far non-parametric approach makes predictions based totally on nearest k-neighbours dataset. widely healthcare scientific studies expect classify sicknesses primarily affected person’s data. intention this work threat growing using rules. Data has been collected from electronic medical records patients diagnosed with healthy individuals. dataset consists various attributes, such as age, gender, body mass index, pressure, cholesterol levels, levels. Information also about lifestyle habits, physical activity, smoking status, alcohol consumption. have pre-processed removing missing values outliers, normalization data done ensure all features same scale. Splitting into training test sets, sets 80% 20% performed. algorithm two groups: those at high risk developing low risk. model's performance assessed variety metrics, including accuracy, precision, recall, F1-score.