Dataset Information

Predictive modeling of housing instability and homelessness in the Veterans Health Administration.

ABSTRACT:

Objective

To develop and test predictive models of housing instability and homelessness based on responses to a brief screening instrument administered throughout the Veterans Health Administration (VHA).

Data sources/study setting

Electronic medical record data from 5.8 million Veterans who responded to the VHA's Homelessness Screening Clinical Reminder (HSCR) between October 2012 and September 2015.

Study design

We randomly selected 80% of Veterans in our sample to develop predictive models. We evaluated the performance of both logistic regression and random forests-a machine learning algorithm-using the remaining 20% of cases.

Data collection/extraction methods

Data were extracted from two sources: VHA's Corporate Data Warehouse and National Homeless Registry.

Principal findings

Performance for all models was acceptable or better. Random forests models were more sensitive in predicting housing instability and homelessness than logistic regression, but less specific in predicting housing instability. Rates of positive screens for both outcomes were highest among Veterans in the top strata of model-predicted risk.

Conclusions

Predictive models based on medical record data can identify Veterans likely to report housing instability and homelessness, making the HSCR screening process more efficient and informing new engagement strategies. Our findings have implications for similar instruments in other health care systems.

SUBMITTER: Byrne T

PROVIDER: S-EPMC6338307 | biostudies-literature | 2019 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predictive modeling of housing instability and homelessness in the Veterans Health Administration.

Byrne Thomas T Montgomery Ann Elizabeth AE Fargo Jamison D JD

Health services research 20180921 1

<h4>Objective</h4>To develop and test predictive models of housing instability and homelessness based on responses to a brief screening instrument administered throughout the Veterans Health Administration (VHA).<h4>Data sources/study setting</h4>Electronic medical record data from 5.8 million Veterans who responded to the VHA's Homelessness Screening Clinical Reminder (HSCR) between October 2012 and September 2015.<h4>Study design</h4>We randomly selected 80% of Veterans in our sample to develo ...[more]

PMID: 30240000

Similar Datasets

Project description:ImportanceThe Veterans Health Administration (VHA) implemented a national clinical program using a suicide risk prediction algorithm, Recovery Engagement and Coordination for Health-Veterans Enhanced Treatment (REACH VET), in which clinicians facilitate care enhancements for individuals identified in local top 0.1% suicide risk tiers. Evaluation studies are needed.ObjectiveTo determine associations with treatment engagement, health care utilization, suicide attempts, safety plan documentation, and 6-month mortality.Design, setting, and participantsThis cohort study used triple differences analyses comparing 6-month changes in outcomes after vs before program entry for individuals entering the REACH VET program (March 2017-December 2018) vs a similarly identified top 0.1% suicide risk tier cohort from prior to program initiation (March 2014-December 2015), adjusting for trends across subthreshold cohorts. Subcohort analyses (including individuals from March 2017-June 2018) evaluated difference-in-differences for cause-specific mortality using death certificate data. The subthreshold cohorts included individuals in the top 0.3% to 0.1% suicide risk tier, below the threshold for REACH VET eligibility, from the concurrent REACH VET period and from the pre-REACH VET period. Data were analyzed from December 2019 through September 2021.ExposuresREACH VET-designated clinicians treatment reevaluation and outreach for care enhancements, including safety planning, increased monitoring, and interventions to enhance coping.Main outcomes and measuresProcess outcomes included VHA scheduled, completed, and missed appointments; mental health visits; and safety plan documentation and documentation within 6 months for individuals without plans within the prior 2 years. Clinical outcomes included mental health admissions, emergency department visits, nonfatal suicide attempts, and all-cause, suicide, and nonsuicide external-cause mortality.ResultsA total of 173 313 individuals (mean [SD] age, 51.0 [14.7] years; 161 264 [93.1%] men and 12 049 [7.0%] women) were included in analyses, including 40 816 individuals eligible for REACH VET care and 36 604 individuals from the pre-REACH VET period in the top 0.1% of suicide risk. The REACH VET intervention was associated with significant increases in completed outpatient appointments (adjusted triple difference [ATD], 0.31; 95% CI, 0.06 to 0.55) and proportion of individuals with new safety plans (ATD, 0.08; 95% CI, 0.06 to 0.10) and reductions in mental health admissions (ATD, -0.08; 95% CI, -0.10 to -0.05), emergency department visits (ADT, -0.03; 95% CI, -0.06 to -0.01), and suicide attempts (ADT, -0.05; 95% CI, -0.06 to -0.03). Subcohort analyses did not identify differences in suicide or all-cause mortality (eg, age-and-sex-adjusted difference-in-difference for suicide mortality, 0.0007; 95% CI, -0.0006 to 0.0019).Conclusions and relevanceThese findings suggest that REACH VET implementation was associated with greater treatment engagement and new safety plan documentation and fewer mental health admissions, emergency department visits, and suicide attempts. Clinical programs using risk modeling may be effective tools to support care enhancements and risk reduction.

Project description:ContextPoor physical and mental health and substance use disorder can be causes and consequences of homelessness. Approximately 2.1 million persons per year in the United States experience homelessness. People experiencing homelessness have high rates of emergency department use, hospitalization, substance use treatment, social services use, arrest, and incarceration.ObjectivesA standard approach to treating homeless persons with a disability is called Treatment First, requiring clients be "housing ready"-that is, in psychiatric treatment and substance-free-before and while receiving permanent housing. A more recent approach, Housing First, provides permanent housing and health, mental health, and other supportive services without requiring clients to be housing ready. To determine the relative effectiveness of these approaches, this systematic review compared the effects of both approaches on housing stability, health outcomes, and health care utilization among persons with disabilities experiencing homelessness.DesignA systematic search (database inception to February 2018) was conducted using 8 databases with terms such as "housing first," "treatment first," and "supportive housing." Reference lists of included studies were also searched. Study design and threats to validity were assessed using Community Guide methods. Medians were calculated when appropriate.Eligibility criteriaStudies were included if they assessed Housing First programs in high-income nations, had concurrent comparison populations, assessed outcomes of interest, and were written in English and published in peer-reviewed journals or government reports.Main outcome measuresHousing stability, physical and mental health outcomes, and health care utilization.ResultsTwenty-six studies in the United States and Canada met inclusion criteria. Compared with Treatment First, Housing First programs decreased homelessness by 88% and improved housing stability by 41%. For clients living with HIV infection, Housing First programs reduced homelessness by 37%, viral load by 22%, depression by 13%, emergency departments use by 41%, hospitalization by 36%, and mortality by 37%.ConclusionsHousing First programs improved housing stability and reduced homelessness more effectively than Treatment First programs. In addition, Housing First programs showed health benefits and reduced health services use. Health care systems that serve homeless patients may promote their health and well-being by linking them with effective housing services.

Project description:INTRODUCTION:This clinical demonstration trial compared the effectiveness of the Veterans Affairs Diabetes Prevention Program (VA-DPP) with an evidence-based usual care weight management program (MOVE!®) in the Veterans Health Administration health system. DESIGN:Prospective, pragmatic, non-randomized comparative effectiveness study of two behavioral weight management interventions. SETTING/PARTICIPANTS:Obese/overweight Veterans with prediabetes were recruited from three geographically diverse VA sites between 2012 and 2014. INTERVENTION:VA-DPP included 22 group-based intensive lifestyle change sessions. MAIN OUTCOME MEASURES:Weight change at 6 and 12 months, hemoglobin A1c (HbA1c) at 12 months, and VA health expenditure changes at 15 months were assessed using VA electronic health record and claims data. Between- and within-group comparisons for weight and HbA1c were done using linear mixed-effects models controlling for age, gender, race/ethnicity, baseline outcome values, and site. Analyses were conducted in 2015-2016. RESULTS:A total of 387 participants enrolled (273 VA-DPP, 114 MOVE!). More VA-DPP participants completed at least one (73.3% VA-DPP vs 57.5% MOVE! p=0.002); four (57.5% VA-DPP vs 42.5% MOVE!, p=0.007); and eight or more sessions (42.5% VA-DPP vs 31% MOVE!, p=0.035). Weight loss from baseline was significant at both 6 (p<0.001) and 12 months (p<0.001) for VA-DPP participants, but only significant at 6 months for MOVE! participants (p=0.004). Between groups, there were significant differences in 6-month weight loss (-4.1 kg VA-DPP vs -1.9 kg MOVE!, p<0.001), but not 12-month weight loss (-3.4 kg VA-DPP vs -2.0 kg MOVE!, p=0.16). There were no significant differences in HbA1c change or outpatient, inpatient, and total VA expenditures. CONCLUSIONS:VA-DPP participants had higher participation rates and weight loss at 6 months, but similar weight, HbA1c, and health expenditures at 12 months compared to MOVE! PARTICIPANTS:Features of VA-DPP may help enhance the capability of MOVE! to reach a larger proportion of the served population and promote individual-level weight maintenance.

Dataset Information

Predictive modeling of housing instability and homelessness in the Veterans Health Administration.

Objective

Data sources/study setting

Study design

Data collection/extraction methods

Principal findings

Conclusions

Publications

Predictive modeling of housing instability and homelessness in the Veterans Health Administration.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets