Prediction And Detection Of Type II Diabetes Mellitus Using The K-Nearest Neighbor Algorithm

Abstract

Purpose: High blood sugar causes Mellitus (DM), a metabolic disorder. DM affects human metabolism and causes many complications, such as heart disease, kidney problems, skin disorders, and slow healing. Therefore, using machine learning algorithms to implement an automatic diabetes diagnosis system is crucial for predicting DM.

Design/methodology/approach: This research created a DM disease prediction system using machine learning with the K-Nearest Neighbor algorithm. The National Institute of Diabetes and Digestive and Kidney Diseases, Hospital Frankfurt, Germany, and the results of health surveys and medical research are the sources of two separate datasets used in the Kaggle platform data. The stages in Machine Learning include data merging, data cleaning, and data splitting

Findings/result: This research produces the best prediction model at a ratio of 70:30, with the lowest MSE value on testing data, 0.217. With K Folding Cross-validation, it makes an average accuracy of 73.88%.

Originality/value/state of the art: This research creates a prediction model for diabetes mellitus type 2 using two different datasets with 9 features. It makes a Machine Learning model using the KNN algorithm by importing the KneighborClassifier and evaluating it using the MSE (Mean Square Error) matrix and K Folding cross-validation to determine modelling accuracy