Developing A Fair Individualized Polysocial Risk Score (iPsRS) for Identifying Increased Social Risk of Hospitalizations in Patients with Type 2 Diabetes (T2D)

TL;DR

This study developed a machine learning-based individualized polysocial risk score (iPsRS) using EHR data to fairly predict hospitalization risk in patients with type 2 diabetes, addressing social determinants of health.

Contribution

The paper introduces a novel EHR-based ML pipeline, iPsRS, incorporating fairness and explainability to identify social risks associated with hospitalizations in T2D patients.

Findings

iPsRS achieved a C statistic of 0.72 in predicting hospitalizations.

The top 5% of patients by iPsRS had a 13-fold higher hospitalization rate.

The method ensures fair risk prediction across racial-ethnic groups.

Abstract

Background: Racial and ethnic minority groups and individuals facing social disadvantages, which often stem from their social determinants of health (SDoH), bear a disproportionate burden of type 2 diabetes (T2D) and its complications. It is therefore crucial to implement effective social risk management strategies at the point of care. Objective: To develop an EHR-based machine learning (ML) analytical pipeline to identify the unmet social needs associated with hospitalization risk in patients with T2D. Methods: We identified 10,192 T2D patients from the EHR data (from 2012 to 2022) from the University of Florida Health Integrated Data Repository, including contextual SDoH (e.g., neighborhood deprivation) and individual-level SDoH (e.g., housing stability). We developed an electronic health records (EHR)-based machine learning (ML) analytic pipeline, namely individualized polysocial risk score (iPsRS), to identify high social risk associated with hospitalizations in T2D patients, along with explainable AI (XAI) techniques and fairness assessment and optimization. Results: Our iPsRS achieved a C statistic of 0.72 in predicting 1-year hospitalization after fairness optimization across racial-ethnic groups. The iPsRS showed excellent utility for capturing individuals at high hospitalization risk; the actual 1-year hospitalization rate in the top 5% of iPsRS was ~13 times as high as the bottom decile. Conclusion: Our ML pipeline iPsRS can fairly and accurately screen for patients who have increased social risk leading to hospitalization in T2D patients.