Search

Objective: To develop easy to use and validated predictive models to identify beneficiaries experiencing homelessness from administrative data. Data Sources: We pooled enrollment and claims data from enrollees of the California Whole Person Care (WPC) Medicaid demonstration program that coordinated the care of a subset of Medicaid beneficiaries identified as high utilizers in 26 California counties (25 WPC Pilots). We also used public directories of social service and health care facilities. Study Design: Using WPC Pilot-reported homelessness status, we trained seven supervised learning algorithms with different specifications to identify beneficiaries experiencing homelessness. The list of predictors included address- and claims-based indicators, demographics, health status, health care utilization, and county-level homelessness rate. We then assessed model performance using measures of balanced accuracy (BA), sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (area under the curve [AUC]). Data Collection/Extraction Methods: We included 93,656 WPC enrollees from 2017 to 2018, 37,441 of whom had a WPC Pilot-reported homelessness indicator. Principal Findings: The random forest algorithm with all available indicators had the best performance (87% BA and 0.95 AUC), but a simpler Generalized Linear Model (GLM) also performed well (74% BA and 0.83 AUC). Reducing predictors to the top 20 and top five most important indicators in a GLM model yields only slightly lower performance (86% BA and 0.94 AUC for the top 20 and 86% BA and 0.91 AUC for the top five). Conclusions: Large samples can be used to accurately predict homelessness in Medicaid administrative data if a validated homelessness indicator for a small subset can be obtained. In the absence of a validated indicator, the likelihood of homelessness can be calculated using county rate of homelessness, address- and claim-based indicators, and beneficiary age using a prediction model presented here. These approaches are needed given the rising prevalence of homelessness and the focus of Medicaid and other payers on addressing homelessness and its outcomes. KEYWORDS administrative data, homelessness, machine learning algorithms, Medicaid What is known on this topic * Homelessness is a social determinant of health and well-established evidence demonstrates that individuals experiencing homelessness have poor health and high use of health care. * Addressing social determinants of health is increasingly a goal of public and private payers and providers, but most lack data on the homelessness status of the populations they serve. * Various methods of identifying homelessness using administrative data have been tried using specific populations and limited data, but their accuracy in determining homelessness is unknown. What this study adds * We identify easy and validated predictive models to identify individuals experiencing homelessness using variables available in administrative data. * We identify the top 20 and top five most important variables in predicting homelessness. * We offer more advanced and simpler but well-performing logit regression models and the related regression coefficients that could be easily applied to identify homelessness., 1 | INTRODUCTION Over half a million persons are estimated to be experiencing homelessness In the United States on a given night. (1) Well-established evidence demonstrates that individuals experiencing homelessness [...]

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.KEYWORDShomelessness, veterans, 1 | INTRODUCTIONHousing instability and especially homelessness, which is an acute form of housing instability, are associated with a range of adverse health outcomes (1,2) and increased costs for health [...]

Objective. To examine the association between reliance on VA outpatient care and hospital admissions among Medicare-eligible Veterans enrolled in the Homeless Patient Aligned Care Team (H-PACT).Data Sources/Study Setting. Registry of H-PACT enrollees linked to VA and Medicare utilization data for 2013.Study Design. After assigning Veterans to two groups according to whether they received >90 percent of outpatient care in VA (higher reliance) or Principal Findings. Compared with higher reliance Veterans, lower reliance Veterans had an equivalent number of annual VA hospitalizations (0.63 vs. 0.50; p = .14) but substantially greater Medicare hospitalizations (0.85 vs. 0.08; p < .001). Among Veterans in the highest tertile of outpatient visits, we observed statistically similar rates of VA hospital use but over 10-fold greater rates of Medicare-financed hospitalizations (1.31 for lower reliance vs. 0.15 for high reliance; p < .001).Conclusions. Among Veterans receiving integrated care in VA's H-PACT, dual use of Medicare and VA outpatient care is strongly associated with acute hospitalizations financed by Medicare. Linking VA and non-VA data may identify a subset of homeless Veterans with fragmented outpatient care who are at increased risk of poor outcomes.Key Words. Veterans, Medicare, homelessness, dual utilization, primary care, Homelessness is common among the Veteran population. Approximately 40,000 Veterans are homeless on any given night, and nearly one-fifth of homeless males in the United States are military Veterans (US [...]

Objective. This study examined variation in the implementation of California's Full Service Partnerships (FSPs), which are supported housing programs that do 'whatever it takes' to improve outcomes among persons with serious mental illness who are homeless or at risk of homelessness. Data Sources/Setting. Ninety-three FSPs in California. Study Design. A mixed methods approach was selected to develop a better understanding of the complexity of the FSP programs. The design structure was a combined explanatory and exploratory sequential design (qual→QUAN→qual) where a qualitative focus group was used to develop a quantitative survey that was followed by qualitative site visits. The survey was used to describe the breadth of variation based on fidelity to the Housing First model, while the site visits were used to provide a depth of information on high- versus low-fidelity programs. Principal Findings. We found substantial variation in implementation among FSPs. Fidelity was particularly low along domains related with housing and service philosophy, indicating that many FSPs implemented a rich array of services but applied housing readiness requirements and did not adhere to consumer choice in housing. Conclusions. There remains room for improvement in the recovery orientation of FSPs. Fortunately, we have identified several processes by which program managers and counties can increase the fidelity of their programs. Key Words. Mental health, homeless populations, health care organizations and systems, On November 2, 2004, California voters approved Proposition 63, which was signed into law as the Mental Health Services Act (MHSA). The MHSA applied a tax of 1 percent on [...]