Towards Transparent and Accurate Diabetes Prediction Using Machine Learning and Explainable Artificial Intelligence

2025-01-30

AI Summary

To address the challenge of simultaneously achieving high predictive accuracy and clinical interpretability in early diabetes screening, this study proposes a novel predictive framework integrating imbalance learning, ensemble modeling, and multi-dimensional eXplainable Artificial Intelligence (XAI). The method systematically combines SMOTE-based oversampling, standardized feature engineering, XGBoost and Random Forest ensemble models, and synergistic attribution analysis via SHAP and LIME. Evaluated on a public dataset, the framework achieves 92.50% accuracy and a ROC-AUC of 0.975—significantly outperforming baseline models. Crucially, it identifies clinically actionable core risk factors—including BMI, age, and self-rated health—and generates a clinically intelligible, ranked list of risk drivers. By jointly optimizing predictive performance and medical trustworthiness, the framework enables the development of deployable, decision-support tools for clinical practice.

Technology Category

• Machine Learning: Ensemble Methods
• Humans and AI: Explainable AI (XAI) for Human Understanding
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Diabetes mellitus (DM) is a global health issue of significance that must be diagnosed as early as possible and managed well. This study presents a framework for diabetes prediction using Machine Learning (ML) models, complemented with eXplainable Artificial Intelligence (XAI) tools, to investigate both the predictive accuracy and interpretability of the predictions from ML models. Data Preprocessing is based on the Synthetic Minority Oversampling Technique (SMOTE) and feature scaling used on the Diabetes Binary Health Indicators dataset to deal with class imbalance and variability of clinical features. The ensemble model provided high accuracy, with a test accuracy of 92.50% and an ROC-AUC of 0.975. BMI, Age, General Health, Income, and Physical Activity were the most influential predictors obtained from the model explanations. The results of this study suggest that ML combined with XAI is a promising means of developing accurate and computationally transparent tools for use in healthcare systems.

Problem

• Diabetes Prediction
• Early Detection
• Disease Management

Innovation

• Machine Learning
• Explainable AI (XAI)
• Diabetes Risk Prediction