What question did this study set out to answer?

This research aims to develop an explainable machine learning framework for predicting type 2 diabetes risk using a two-stage approach.

March 31, 2026Open Access

Early Type 2 diabetes risk prediction using explainable machine learning in a two-stage approach

Key Points

This research aims to develop an explainable machine learning framework for predicting type 2 diabetes risk using a two-stage approach.
Developed five machine learning models: MLP, SVM, KNN, XGBoost, and Naïve Bayes.
Stage one utilized a public dataset of 520 samples for feature selection using SHAP and MLP weights.
Stage two involved training the models on a larger dataset of 270,943 samples from Rwanda.
Employed SHAP for further model output explanation in both stages.
MLP model achieved 95.19% accuracy in Stage one on the public dataset.
Ten influential predictors of diabetes risk were identified.
XGBoost model outperformed others in Stage two with an accuracy of 97.14%.
The framework enhances screening for diabetes within the mUzima mobile application.

Abstract

Background Diabetes is a chronic disease characterized by elevated blood glucose levels. Without early detection and proper management, it can lead to serious complications and increase healthcare costs. Its global prevalence is rising, with many cases remaining undiagnosed. In this study, we developed an explainable machine learning model using a two-stage approach for predicting diabetes. Methods Five machine learning (ML) models, including Multi-Layer Perceptron, Support Vector Machine, K-Nearest Neighbor, Extreme Gradient Boosting (XGBoost), and Naïve Bayes, were trained and evaluated using a two-stage approach. In Stage one, a public dataset containing 520 samples was used, and Shapley Additive exPlanations (SHAP) and MLP weights were applied for feature selection. In Stage two, the same models were trained and evaluated using a dataset of 270,943 samples collected from Rwanda. SHAP was further employed to explain the model output. Results In Stage one, the Multi-Layer Perceptron model achieved the best performance on a public dataset, with an accuracy of 95.19%. Feature selection techniques identified the top 10 influential predictors associated with diabetes risk, including those recommended by diabetes care providers in Rwanda. In Stage two, the XGB model outperformed other models, achieving an accuracy of 97.14%. Conclusion This study presents a two-stage, explainable machine learning framework for systematic screening for type 2 diabetes. The first stage evaluates risk based on reported symptoms, while the second stage incorporates demographic, anthropometric, and vital sign data for refined risk assessment. Integration of these models into the mUzima mobile application can enhance community health workers' capacity to identify and refer high-risk individuals. By enabling early and accurate detection, the proposed approach has the potential to reduce undiagnosed diabetes and support improved disease management.

AI에게 질문

Bookmark

View Full Paper