Comparative Analysis of Machine Learning Methods in Predicting Diabetes Risk Based on Genetic Data

Type 2 Diabetes Mellitus (T2DM) is a global chronic disease caused by the interaction of genetic and environmental factors. The use of genetic data offers great potential for early detection and personalized intervention. However, the complex analysis of genetic data requires sophisticated approaches like machine learning. This study aims to compare the performance of three machine learning algorithms Logistic Regression, Random Forest, and K-Nearest Neighbors (KNN) in predicting T2DM risk based on genetic data. By using a Systematic Literature Review of studies published between 2019 and 2024, the accuracy data from each algorithm was compared. The analysis results show that Random Forest has the best performance with an accuracy of 99.3%. This algorithm excels due to its ability to handle high-dimensional datasets and reduce overfitting. In comparison, KNN achieved an accuracy of 87% and Logistic Regression 82%. These findings support the integration of machine learning into early detection systems and more precise and efficient clinical decision-making for T2DM management.