Problem
Identifying and connecting of patients with Health Related Social Needs (HRSN) to resources is a complicated gauntlet with multiple potential points for failure. Due to these challenges, rates for connecting a patient to a Community-Based Organization (CBO) and a resource are often considered successful in the range of 15-30%. We have identified three points of failure to successfully place a referral. These include recognition of a domain need, identification of the patient’s assent for help, and, finally, placing of referrals in NCCARE360.
Solution
We propose improving EHR integration and management of HRSNs by implementing the Compass Rose module in Epic and reconfiguring our NCCARE360 integration to support bidirectional data flows. Using an auto-enroll feature for recently discharged patients who meet the criteria for Meals on Wheels service, we will gain efficiency. We propose using generative AI/LLM to summarize patients’ HRSN status in the EHR, referrals placed, and risks for readmission into a note called Discharge HRSN Assessment.
Impact
IP eCQM #487 requires reporting for social determinants of health (SDOH) screening rates and volume of patients with HRSNs. We anticipate an increase in the number of patients identified with HRSNs. We seek to meet the needs of our patients through automatic formats to place referrals, get consent for ROI, and a generative AI report to summarize HRSN status at discharge. We anticipate the sum of these interventions will support smoother transitions of care, decreases in readmissions, and improvements in health outcomes.
