Integrating Explainable Machine Learning Techniques for Predicting Diabetes: A Transparent Approach to AI-Driven Healthcare

Abstract: Diabetes mellitus is a global health concern affecting millions worldwide, with profound medical and socioeconomic implications. The increasing adoption of machine learning (ML) in healthcare has revolutionized clinical decision-making by enabling predictive diagnostics, personalized treatment plans, and efficient resource allocation. Despite their potential, many ML models are often regarded as "black boxes" due to their lack of transparency, which raises significant challenges in critical fields like healthcare, where explainability is crucial for ethical and accountable decision-making (Hassija et al., 2024).Explainable Artificial Intelligence (XAI) has emerged as a solution to address these challenges by making ML models more interpretable and fostering trust among healthcare practitioners and patients. This paper explores the integration of XAI techniques with ML models for diabetes prediction, emphasizing their potential to enhance transparency, trust, and clinical utility. We present a comparative analysis of popular XAI methods, such as SHAP (Shapley Additive Explanations), LIME (Local Interpretable Model-agnostic Explanations), and attention mechanisms, within the context of healthcare decision support. These techniques are evaluated based on interpretability, computational efficiency, and clinical applicability, highlighting the trade-offs between accuracy and transparency.The study underscores the critical role of interpretability in advancing trust and adoption of AI-driven solutions in healthcare, while addressing challenges such as balancing model performance with explainability. Finally, future directions for deploying explainable ML in healthcare are outlined, aiming to ensure ethical, transparent, and effective AI implementation.

Keywords: Explainable Artificial Intelligence (XAI), Predicting Diabetes, AI-Driven Healthcare

DOI: 10.54941/ahfe1006203

Cite this paper:

​