An Explainable AI-Driven Framework for Sustainable Supplier Selection in Healthcare Systems: A Methodological Framework and Proof of Concept

Supplier selection in healthcare is a complex multi-criteria decision-making (MCDM) challenge requiring a balance of sustainability, resilience, and operational efficiency. Traditional methods struggle with scalability and subjectivity when applied to large administrative datasets. This study introduces a transparent hybrid Machine Learning–MCDM (ML–MCDM) framework, validated using a U.S. Medicare dataset of 661 suppliers. The framework integrates eXtreme Gradient Boosting (XGBoost) and SHapley Additive exPlanations (SHAP) for criterion prioritization, the Full Consistency Method (FUCOM) for mathematically consistent weighting, and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for final ranking. As the dataset lacks direct sustainability metrics, seven indicators were synthetically generated; thus, the results serve as proof-of-concept demonstration of the framework’s architecture. Specifically, XGBoost–SHAP is trained to predict a synthetically constructed Overall Performance Score (OPS), meaning that the resulting feature importance output constitutes an algorithmic consistency check—confirming that the pipeline correctly recovers importance signals deliberately embedded in the training target. For interpretability, suppliers were segmented into five performance profiles via K-Means: Strategic Partners (17.7%), Green Leaders (18.6%), Reliable Emergency Suppliers (18.2%), Balanced Performers (20.4%), and Developing Suppliers (25.1%). Carbon Footprint Score (0.408) and Emergency Response Capability (0.316) achieved the highest feature importance. FUCOM-derived weights prioritized On-Time Delivery Rate (0.272), Carbon Footprint Score (0.222), and Emergency Response Capability (0.220). The top supplier attained a TOPSIS closeness coefficient of 0.800, showing strong discrimination. Sensitivity analysis across four scenarios confirmed ranking robustness, maintaining Spearman correlations ρ ≥ 0.977. This ML–FUCOM–TOPSIS approach provides an auditable, scalable, and policy-relevant decision-support tool, enabling procurement managers to navigate high-dimensional data while ensuring operational continuity and environmental responsibility in healthcare supply chains.