Show simple item record

dc.contributor.authorByrne, Thomasen_US
dc.contributor.authorMontgomery, Ann Elizabethen_US
dc.contributor.authorFargo, Jamison D.en_US
dc.date.accessioned2020-05-05T18:01:02Z
dc.date.available2020-05-05T18:01:02Z
dc.date.issued2019-02-01
dc.identifierhttp://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000456192200008&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=6e74115fe3da270499c3d65c9b17d654
dc.identifier.citationThomas Byrne, Ann Elizabeth Montgomery, Jamison D Fargo. 2019. "Predictive modeling of housing instability and homelessness in the Veterans Health Administration." HEALTH SERVICES RESEARCH, Volume 54, Issue 1, pp. 75 - 85 (11). https://doi.org/10.1111/1475-6773.13050
dc.identifier.issn0017-9124
dc.identifier.issn1475-6773
dc.identifier.urihttps://hdl.handle.net/2144/40571
dc.description.abstractOBJECTIVE: 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.en_US
dc.description.sponsorshipU.S. Department of Veterans Affairs (VA) Health Services Research and Development (HSR&D), Grant/Award Number: IIR 13-334 (IIR 13-334 - U.S. Department of Veterans Affairs (VA) Health Services Research and Development (HSRD))en_US
dc.format.extentp. 75 - 85en_US
dc.languageEnglish
dc.language.isoen_US
dc.publisherWILEYen_US
dc.relation.ispartofHEALTH SERVICES RESEARCH
dc.subjectScience & technologyen_US
dc.subjectLife sciences & biomedicineen_US
dc.subjectHealth care sciences & servicesen_US
dc.subjectHealth policy & servicesen_US
dc.subjectHomelessnessen_US
dc.subjectVeteransen_US
dc.subjectSocial determinantsen_US
dc.subjectPrimary careen_US
dc.subjectRisk factorsen_US
dc.subjectServicesen_US
dc.subjectCostsen_US
dc.subjectAdulten_US
dc.subjectFemaleen_US
dc.subjectHomeless personsen_US
dc.subjectHumansen_US
dc.subjectMaleen_US
dc.subjectMiddle ageden_US
dc.subjectPublic assistanceen_US
dc.subjectPublic housingen_US
dc.subjectUnited Statesen_US
dc.subjectUnited States Department of Veterans Affairsen_US
dc.subjectVeterans healthen_US
dc.subjectHealth policy & servicesen_US
dc.subjectPublic health and health servicesen_US
dc.titlePredictive modeling of housing instability and homelessness in the Veterans Health Administrationen_US
dc.typeArticleen_US
dc.description.versionAccepted manuscripten_US
dc.identifier.doi10.1111/1475-6773.13050
pubs.elements-sourceweb-of-scienceen_US
pubs.notesEmbargo: No embargoen_US
pubs.organisational-groupBoston Universityen_US
pubs.organisational-groupBoston University, School of Social Worken_US
pubs.publication-statusPublisheden_US
dc.identifier.orcid0000-0003-4824-0284 (Byrne, Thomas)
dc.identifier.mycv398997


This item appears in the following Collection(s)

Show simple item record