Using social risks to predict unplanned hospital readmission and emergency care among hospitalized Veterans.

OBJECTIVES: (1) To estimate the association of social risk factors with unplanned readmission and emergency care after a hospital stay. (2) To create a social risk scoring index. DATA SOURCES AND SETTING: We analyzed administrative data from the Department of Veterans Affairs (VA) Corporate Data Warehouse. Settings were VA medical centers that participated in a national social work staffing program. STUDY DESIGN: We grouped socially relevant diagnoses, screenings, assessments, and procedure codes into nine social risk domains. We used logistic regression to examine the extent to which domains predicted unplanned hospital readmission and emergency department (ED) use in 30 days after hospital discharge. Covariates were age, sex, and medical readmission risk score. We used model estimates to create a percentile score signaling Veterans' health-related social risk. DATA EXTRACTION: We included 156,690 Veterans' admissions to a VA hospital with discharged to home from 1 October, 2016 to 30 September, 2022. PRINCIPAL FINDINGS: The 30-day rate of unplanned readmission was 0.074 and of ED use was 0.240. After adjustment, the social risks with greatest probability of readmission were food insecurity (adjusted probability = 0.091 [95% confidence interval: 0.082, 0.101]), legal need (0.090 [0.079, 0.102]), and neighborhood deprivation (0.081 [0.081, 0.108]); versus no social risk (0.052). The greatest adjusted probabilities of ED use were among those who had experienced food insecurity (adjusted probability 0.28 [0.26, 0.30]), legal problems (0.28 [0.26, 0.30]), and violence (0.27 [0.25, 0.29]), versus no social risk (0.21). Veterans with social risk scores in the 95th percentile had greater rates of unplanned care than those with 95th percentile Care Assessment Needs score, a clinical prediction tool used in the VA. CONCLUSIONS: Veterans with social risks may need specialized interventions and targeted resources after a hospital stay. We propose a scoring method to rate social risk for use in clinical practice and future research.

Building Tailored Resource Guides to Address Social Risks and Advance Health Equity in the Veterans Health Administration.

Background: Health care organizations, including the Veterans Health Administration (VHA), are increasingly adopting programs to address social determinants of health. As part of a comprehensive social risk screening and referral model, tailored resource guides can support efforts to address unmet social needs. However, limited guidance is available on best practices for the development of resource guides in health care settings. Observations: This article describes the development of geographically tailored resource guides for a national VHA quality improvement initiative, Assessing Circumstances and Offering Resources for Needs (ACORN), which aims to systematically screen for and address social needs among veterans. We outline the rationale for using resource guides as a social needs intervention and provide a pragmatic framework for resource guide development and maintenance. We offer guidance based on lessons learned from the development of ACORN resource guides, emphasizing a collaborative approach with VHA social workers and other frontline clinical staff, as well as with community-based organizations. Our how-to guide provides steps for identifying high-yield resources along with formatting considerations to maximize accessibility and usability among patients. Conclusions: Resource guides can serve as a valuable cross-cutting component of health care organizations' efforts to address social needs. We provide a practical approach to resource guide development that may support successful implementation within the VHA and other clinical settings.

Benefits and challenges in the use of RE-AIM for evaluation of a national social work staffing program in the veterans health administration.

Background: In the Department of Veterans Affairs (VA) Veterans Health Administration (VHA), social workers embedded in primary care teams address social and emotional needs that are associated with health outcomes. The mission of the National Social Work PACT Staffing Program is to improve access to social work services for rural Veterans by supporting additional social work staffing in VA medical centers serving rural areas. Methods: We obtained data from the VA corporate data warehouse on Veterans' characteristics and health care use from 2016 to 2022 for all Veterans who received primary care at a Veterans Affairs Medical Center (VAMC) or associated clinic that received funding from the program. We evaluated the program according to RE-AIM constructs as follows: Reach [total number of Veterans who engaged with PACT social work and representativeness with regard to race, rural residence, chronic conditions and health behaviors, and hospital and emergency department (ED) use in the previous 12 months]; Effectiveness (impact of the program on key health care use outcomes which include hospitalizations, emergency department visits, and palliative care); Adoption (number of VA medical centers and outpatient clinics serving rural Veterans that have participated in the program, and number and representativeness of sites eligible for program participation that have not yet received funding); Implementation (adherence to standardized note templates), and Maintenance (permanent social work positions created by the program and continued technical support). Results: In 2022, the program engaged with 30,982 Veterans, 65% of whom lived in rural areas. The program increased social work encounters, reduce hospital and emergency department use, and increase use of palliative care services among Veterans. Key elements of implementation include proactive outreach to Veterans with high-risk indicators and assessment for social risk factors using standardized, national note templates. In terms of maintenance, the program continues to provide data and technical assistance to 23 sites and has created 171 permanent social work positions. Conclusions and implications: The Social Work PACT Staffing Program demonstrates positive outcomes and program sustainment. The RE-AIM framework was a useful tool to evaluate the program, but additional adaption was needed to fit the program's needs.

Social Work Staffing and Use of Palliative Care Among Recently Hospitalized Veterans.

Importance: Palliative care improves quality of life for patients and families but may be underused. Objective: To assess the association of an intervention to increase social work staffing in Veterans Health Administration primary care teams with use of palliative care among veterans with a recent hospitalization. Design, Setting, and Participants: This cohort study used differences-in-differences analyses of the change in palliative care use associated with implementation of the Social Work Patient Aligned Care Team (PACT) staffing program, conducted from October 1, 2016, to September 30, 2019. The study included 71 VA primary care sites serving rural veterans. Participants were adult veterans who received primary care services from a site enrolled in the program and who received inpatient hospital care. Data were analyzed from January 2020 to August 2022. Exposures: The PACT staffing program was a clinic-level intervention that provided 3-year seed funding to Veterans Health Administration medical centers to hire 1 or more additional social workers in primary care teams. Staggered timing of the intervention enabled comparison of mean outcomes across sites before and after the intervention. Main Outcomes and Measures: The primary outcome was the number of individuals per 1000 veterans who had any palliative care use in 30 days after an inpatient hospital stay. Results: The analytic sample included 43 200 veterans (mean [SD] age, 65.34 [13.95] years; 37 259 [86.25%] men) and a total of 91 675 episodes of inpatient hospital care. Among the total cohort, 8611 veterans (9.39%) were Black, 77 069 veterans (84.07%) were White, and 2679 veterans (2.92%) were another race (including American Indian or Alaskan Native, Asian, and Native Hawaiian or other Pacific Islander). A mean of 14.5 individuals per 1000 veterans (1329 individuals in all) used palliative care after a hospital stay. After the intervention, there was an increase of 15.6 (95% CI, 9.2-22.3) individuals per 1000 veterans using palliative or hospice care after a hospital stay, controlling for national time trends and veteran characteristics-a 2-fold difference relative to the mean. Conclusions and Relevance: This cohort study found significant increases in use of palliative care for recently hospitalized veterans whose primary care team had additional social work staffing. These findings suggest that social workers may increase access to and/or use of palliative care. Future work should assess the mechanism for this association and whether the increase in palliative care is associated with other health or health care outcomes.

Adaptation of a social risk screening and referral initiative across clinical populations, settings, and contexts in the Department of Veterans Affairs Health System.

Identifying and addressing social risks and social needs in healthcare settings is an important step towards achieving health equity. Assessing Circumstances and Offering Resources for Needs (ACORN) is a Department of Veterans Affairs (VA) social risk screening and referral model that aims to systematically identify and address social needs. Since initial piloting in 2018, our team has collaborated with clinical and operations partners to implement ACORN across multiple VA clinical settings while adapting and tailoring the initiative to meet the needs of different populations, specialties, and individuals administering screening. Given ACORN's complexity as a growing initiative with multiple partners and frequent real-time modifications within a large national healthcare system, we recognized a need to systematically document the rationale and process of adaptations over time. We looked to three implementation frameworks-RE-AIM, the Adaptome, and FRAME-to describe the rationale for adaptations, the nature of and context within which adaptations were made, and the details of each adaptation. In this manuscript, we uniquely interweave these three frameworks to document adaptations to ACORN across diverse VA clinical settings, with a focus on how adaptations support the promotion of heath equity in the Veteran population.

Social work and telehealth: How Patient Aligned Care Team (PACT) social workers in the Veterans Health Administration responded to COVID-19.

In March 2020, the Veterans Health Administration (VA) responded to pandemic shutdowns with a rapid pivot toward providing services via telehealth. Using data on Veterans who received interventions from social workers between 2019 and 2020 at sites that participated in a national program to increase social work staffing in primary care, we examined changes in frequency and modality of social work encounters that occurred with the onset of the COVID-19 pandemic. We found that primary care social workers maintained a consistent level of engagement, with increases in telephone and video telehealth encounters as in-person visits decreased. Through front-line perspectives, we discuss the practical innovations and policies that enabled those changes in care from VA primary care social workers.

Measuring Adoption of Patient Priorities-Aligned Care Using Natural Language Processing of Electronic Health Records: Development and Validation of the Model.

BACKGROUND: Patient Priorities Care (PPC) is a model of care that aligns health care recommendations with priorities of older adults who have multiple chronic conditions. Following identification of patient priorities, this information is documented in the patient's electronic health record (EHR). OBJECTIVE: Our goal is to develop and validate a natural language processing (NLP) model that reliably documents when clinicians identify patient priorities (ie, values, outcome goals, and care preferences) within the EHR as a measure of PPC adoption. METHODS: This is a retrospective analysis of unstructured National Veteran Health Administration EHR free-text notes using an NLP model. The data were sourced from 778 patient notes of 658 patients from encounters with 144 social workers in the primary care setting. Each patient's free-text clinical note was reviewed by 2 independent reviewers for the presence of PPC language such as priorities, values, and goals. We developed an NLP model that utilized statistical machine learning approaches. The performance of the NLP model in training and validation with 10-fold cross-validation is reported via accuracy, recall, and precision in comparison to the chart review. RESULTS: Of 778 notes, 589 (75.7%) were identified as containing PPC language (kappa=0.82, P<.001). The NLP model in the training stage had an accuracy of 0.98 (95% CI 0.98-0.99), a recall of 0.98 (95% CI 0.98-0.99), and precision of 0.98 (95% CI 0.97-1.00). The NLP model in the validation stage had an accuracy of 0.92 (95% CI 0.90-0.94), recall of 0.84 (95% CI 0.79-0.89), and precision of 0.84 (95% CI 0.77-0.91). In contrast, an approach using simple search terms for PPC only had a precision of 0.757. CONCLUSIONS: An automated NLP model can reliably measure with high precision, recall, and accuracy when clinicians document patient priorities as a key step in the adoption of PPC.

Embedding Social Workers In Veterans Health Administration Primary Care Teams Reduces Emergency Department Visits.

While an emerging body of evidence suggests that medical homes may yield more benefits than traditional care models do, the role of social workers within medical homes has yet to be evaluated separately. We assessed the impact of an initiative to add social workers to rural primary care teams in the Veterans Health Administration on patients' use of social work services, hospital admissions, and emergency department visits. We found that introducing a social worker increased social work encounters by 33 percent among all veterans who received care. Among high-risk patients, we observed a 4.4 percent decrease in the number of veterans who had any acute hospital admission and a 3.0 percent decrease in veterans who had any emergency department visit, after the introduction of a social worker. Investing in social workers is a key strategy for addressing the social determinants of health and managing care coordination for high-risk, high-need populations.