Understanding the Role of a Technology and EMR-based Social Determinants of Health Screening Tool and Community-based Resource Connections in Health Care Resource Utilization.

Health systems are increasingly investing in social determinants of health (SDoH), but there is limited research on how such efforts impact health care resource use. This study presents pilot work on an SDoH screening and referral platform recently implemented in South Carolina's largest private nonprofit health system. To assess the feasibility and sustainability of SDoH screening and SDoH-related referrals in a large health system and examine how they affect health resource use. Observational study using electronic medical records and SDoH screening data from June 1, 2019 to December 31, 2020. Patients (18 y+) engaged in community health, inpatient case management, or ambulatory care and condition management programs. We describe the use of SDoH screening by providers (community health workers, nurse case managers, and social workers) and SDoH referral volumes among patients. We use multivariate analyses to predict changes in emergency department visits, inpatient admission s (length of stay and volume), and primary care visits from referral volume, SDoH screening question responses, and patient characteristics (eg, comorbidities). Of 2687 patients, 662 (24.6%) screened positive for 1 or more SDoH domains. SDoH screening performance remained consistent among providers over time. Six hundred fifty-eight (24.5%) patients received SDoH referrals. Patients receiving an increasing volume of referrals had decreasing primary care visits but their comorbidities moderated this effect. The study provides initial descriptive information on SDoH needs, implementation of referrals and resource use, guiding SDoH screening implementation in population health, and care management programs.

Gupta D ，Self S ，Thomas D ，Supra J ，Rudisill C ... -  《-》

Integrating Social Determinants of Health in Machine Learning-Driven Decision Support for Diabetes Case Management: Protocol for a Sequential Mixed Methods Study.

The use of both clinical factors and social determinants of health (SDoH) in referral decision-making for case management may improve optimal use of resources and reduce outcome disparities among patients with diabetes. This study proposes the development of a data-driven decision-support system incorporating interactions between clinical factors and SDoH into an algorithm for prioritizing who receives case management services. The paper presents a design for prediction validation and preimplementation assessment that uses a mixed methods approach to guide the implementation of the system. Our study setting is a large, tertiary care academic medical center in the Deep South of the United States, where SDoH contribute to disparities in diabetes-specific hospitalizations and emergency department (ED) visits. This project will develop an interpretable artificial intelligence model for a population with diabetes using SDoH and clinical data to identify which posthospitalization cases have a higher likelihood of subsequent ED use. The electronic health record data collected for the study include demographics, SDoH, comorbidities, hospitalization-related factors, laboratory test results, and medication use to predict posthospitalization ED visits. Subsequently, a mixed methods approach will be used to validate prediction outcomes and develop an implementation strategy from insights into patient outcomes from case managers, clinicians, and quality and patient safety experts. As of December 2023, we had abstracted data on 174,871 inpatient encounters between January 2018 and September 2023, involving 89,355 unique inpatients meeting inclusion criteria. Both clinical and SDoH data items were included for these patient encounters. In total, 85% of the inpatient visits (N=148,640) will be used for training (learning from the data) and the remaining 26,231 inpatient visits will be used for mixed-methods validation (testing). By integrating a critical suite of SDoH with clinical data related to diabetes, the proposed data-driven risk stratification model can enable individualized risk estimation and inform health professionals (eg, case managers) about the risk of patients' upcoming ED use. The prediction outcome could potentially automate case management referrals, helping to better prioritize services. By taking a mixed methods approach, we aim to align the model with the hospital's specific quality and patient safety considerations for the quality of patient care and the optimization of case management resource allocation. DERR1-10.2196/56049.

Lee SY ，Hayes LW ，Ozaydin B ，Howard S ，Garretson AM ，Bradley HM ，Land AM ，DeLaney EW ，Pritchett AO ，Furr AL ，Allgood A ，Wyatt MC ，Hall AG ，Banaszak-Holl JC ... -  《-》

Implementing an EHR-based Screening and Referral System to Address Social Determinants of Health in Primary Care.

Buitron de la Vega P ，Losi S ，Sprague Martinez L ，Bovell-Ammon A ，Garg A ，James T ，Ewen AM ，Stack M ，DeCarvalho H ，Sandel M ，Mishuris RG ，Deych S ，Pelletier P ，Kressin NR ... -  《-》

Evaluation of a social determinants of health screening questionnaire and workflow pilot within an adult ambulatory clinic.

There is increased recognition in clinical settings of the importance of documenting, understanding, and addressing patients' social determinants of health (SDOH) to improve health and address health inequities. This study evaluated a pilot of a standardized SDOH screening questionnaire and workflow in an ambulatory clinic within a large integrated health network in Northern California. The pilot screened for SDOH needs using an 11-question Epic-compatible paper questionnaire assessing eight SDOH and health behavior domains: financial resource, transportation, stress, depression, intimate partner violence, social connections, physical activity, and alcohol consumption. Eligible patients for the pilot receiving a Medicare wellness, adult annual, or new patient visits during a five-week period (February-March, 2020), and a comparison group from the same time period in 2019 were identified. Sociodemographic data (age, sex, race/ethnicity, and payment type), visit type, length of visit, and responses to SDOH questions were extracted from electronic health records, and a staff experience survey was administered. The evaluation was guided by the Reach, Effectiveness, Adoption, Implementation, and Maintenance (RE-AIM) framework. Two-hundred eighty-nine patients were eligible for SDOH screening. Responsiveness by domain ranged from 55 to 67%, except for depression. Half of patients had at least one identified social need, the most common being stress (33%), physical activity (22%), alcohol (12%), and social connections (6%). Physical activity needs were identified more in females (81% vs. 19% in males, p < .01) and at new patient/transfer visits (48% vs. 13% at Medicare wellness and 38% at adult wellness visits, p < .05). Average length of visit was 39.8 min, which was 1.7 min longer than that in 2019. Visit lengths were longer among patients 65+ (43.4 min) and patients having public insurance (43.6 min). Most staff agreed that collecting SDOH data was relevant and accepted the SDOH questionnaire and workflow but highlighted opportunities for improvement in training and connecting patients to resources. Use of evidence-based SDOH screening questions and associated workflow was effective in gathering patient SDOH information and identifying social needs in an ambulatory setting. Future studies should use qualitative data to understand patient and staff experiences with collecting SDOH information in healthcare settings.

Berkowitz RL ，Bui L ，Shen Z ，Pressman A ，Moreno M ，Brown S ，Nilon A ，Miller-Rosales C ，Azar KMJ ... -  《BMC Family Practice》

Social Determinants of Health Screening at an Urban Emergency Department Urgent Care During COVID-19.

Hong H ，Shankar KN ，Thompson A ，De La Vega PB ，Koul R ，Cleveland Manchanda EC ，Jaiprasert S ，Roberts S ，Pina T ，Anderson E ，Lin J ，Jacquet GA ... -  《-》