An Improved Ensemble-Based Machine Learning Model with Feature Optimization for Early Diabetes Prediction

2025-11-15

AI Summary

Balancing predictive accuracy and clinical interpretability remains challenging in early diabetes prediction. Method: We propose an interpretable, high-performance machine learning framework: (1) addressing class imbalance in the BRFSS dataset via SMOTE-Tomek Links; (2) constructing a stacking ensemble model centered on XGBoost and KNN, with comparative feature importance analysis and optimization across base learners (Random Forest, CatBoost, LightGBM); and (3) developing a lightweight React Native mobile application for seamless clinical deployment and real-time risk assessment. Results: The framework achieves 94.82% accuracy, ROC-AUC of 0.989, and PR-AUC of 0.991 on the BRFSS dataset—outperforming individual models—while preserving model transparency and clinical utility. It delivers a practical, deployable AI decision-support tool for primary-care diabetes risk screening.

Technology Category

• Machine Learning: Transparent, Interpretable, Explainable ML
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Diabetes is a serious worldwide health issue, and successful intervention depends on early detection. However, overlapping risk factors and data asymmetry make prediction difficult. To use extensive health survey data to create a machine learning framework for diabetes classification that is both accurate and comprehensible, to produce results that will aid in clinical decision-making. Using the BRFSS dataset, we assessed a number of supervised learning techniques. SMOTE and Tomek Links were used to correct class imbalance. To improve prediction performance, both individual models and ensemble techniques such as stacking were investigated. The 2015 BRFSS dataset, which includes roughly 253,680 records with 22 numerical features, is used in this study. Strong ROC-AUC performance of approximately 0.96 was attained by the individual models Random Forest, XGBoost, CatBoost, and LightGBM.The stacking ensemble with XGBoost and KNN yielded the best overall results with 94.82% accuracy, ROC-AUC of 0.989, and PR-AUC of 0.991, indicating a favourable balance between recall and precision. In our study, we proposed and developed a React Native-based application with a Python Flask backend to support early diabetes prediction, providing users with an accessible and efficient health monitoring tool.

Problem

• Develops an ensemble ML model for early diabetes prediction
• Addresses class imbalance and data asymmetry in health datasets
• Creates a mobile application for accessible diabetes risk assessment

Innovation

• Ensemble stacking with XGBoost and KNN for high accuracy
• SMOTE and Tomek Links to address class imbalance
• React Native app with Flask backend for prediction tool