Acceptance of Automated Social Risk Scoring in the EmergencyDepartment: Clinician, Staff, and Patient Perspectives

Introduction: Healthcare organizations are under increasing pressure from policymakers, payers, andadvocates to screen for and address patients'health-related social needs (HRSN). The emergencydepartment (ED) presents several challenges to HRSN screening, and patients are frequently notscreened for HRSNs. Predictive modeling using machine learning and artificial intelligence, approachesmay address some pragmatic HRSN screening challenges in the ED. Because predictive modelingrepresents a substantial change from current approaches, in this study we explored the acceptability ofHRSN predictive modeling in the ED. Methods: Emergency clinicians, ED staff, and patient perspectives on the acceptability and usage ofpredictive modeling for HRSNs in the ED were obtained through in-depth semi-structured interviews(eight per group, total 24). All participants practiced at or had received care from an urban, Midwest,safety-net hospital system. We analyzed interview transcripts using a modified thematic analysisapproach with consensus coding. Results: Emergency clinicians, ED staff, and patients agreed that HRSN predictive modeling must leadto actionable responses and positive patient outcomes. Opinions about using predictive modeling resultsto initiate automatic referrals to HRSN services were mixed. Emergency clinicians and staff wantedtransparency on data inputs and usage, demanded high performance, and expressed concern forunforeseen consequences. While accepting, patients were concerned that prediction models can missindividuals who required services and might perpetuate biases. Conclusion: Emergency clinicians, ED staff, and patients expressed mostly positive views about usingpredictive modeling for HRSNs. Yet, clinicians, staff, and patients listed several contingent factorsimpacting the acceptance and implementation of HRSN prediction models in the ED. [West J EmergMed. 2024;25(4)614-623.]