SHAP-Based Explainable Clustering for Medical Records Insights

Machine Learning enables data-driven decision-making in various fields, including healthcare. Clustering techniques, widely used for patient segmentation, can enhance medical coverage management. However, ethical concerns arise regarding the use of Machine Learning, particularly in critical areas where biases can significantly impact people's well-being. This work explores the application of SHAP-based explainable clustering to the SOSUNC (Servicio de Obra Social de la Universidad Nacional del Comahue) in Neuquén, Argentina. By developing a Machine Learning workflow for data processing, clustering, and analysis, this study aims to support better decision-making in medical coverage and policy planning.