Hospital-based preventative interventions for people experiencing homelessness in high-income countries: A systematic review

Abstract

Background: People experiencing homelessness have significant unmet needs and high rates of unplanned care. We aimed to describe preventative interventions, defined in their broadest sense, for people experiencing homelessness in a hospital context. Secondary aims included mapping outcomes and assessing intervention effectiveness.

Methods: We searched online databases (MEDLINE, Embase, PsycINFO, HMIC, CINAHL, Web of Science, Cochrane Library) from 1999-2019 and conducted backward and forward citation searches to 31 December 2020 (PROSPERO CRD42019154036). We included quantitative studies in emergency and inpatient settings measuring health or social outcomes for adults experiencing homelessness in high income countries. We assessed rigour using the "Quality Assessment Tool for Quantitative Studies" and summarised findings using descriptive quantitative methods, a binomial test, a Harvest Plot, and narrative synthesis. We used PRISMA and SWiM reporting guidelines.

Findings: Twenty-eight studies identified eight intervention types: care coordination (n=18); advocacy, support, and outreach (n=13); social welfare assistance (n=13); discharge planning (n=12); homelessness identification (n=6); psychological therapy and treatment (n=6); infectious disease prevention (n=5); and screening, treatment, and referrals (n=5). The evidence strength was weak (n=16) to moderate (n=10), with two high quality randomised controlled trials. We identified six outcome categories with potential benefits observed for psychosocial outcomes, including housing (11/13 studies, 95%CI=54.6-98.1%, p=0.023), healthcare use (14/17, 56.6-96.2%, p=0.013), and healthcare costs (8/8, 63.1-100%, p=0.008). Benefits were less likely for health outcomes (4/5, 28.3-99.5%, p=0.375), integration with onward care (2/4, 6.8-93.2%, p=1.000), and feasibility/acceptability (5/6, 35.9-99.6%, p=0.219), but confidence intervals were very wide. We observed no harms. Most studies showing potential benefits were multi-component interventions.

Interpretation: Hospital-based preventative interventions for people experiencing homelessness are potentially beneficial, but more rigorous research is needed. In the context of high needs and extreme inequities, policymakers and healthcare providers may consider implementing multi-component preventative interventions.

Funding: SL is supported by an NIHR Clinical Doctoral Research Fellowship (ICA-CDRF-2016-02-042). JD is supported by an NIHR School of Public Health Research Pre-doctoral Fellowship (NU-004252). RWA is supported by a Wellcome Clinical Research Career Development Fellowship (206602).

Keywords: ED, Emergency Department; Health inequalities; Homeless persons; Hospital; Multicomponent interventions; Prevention; RCT, Randomised Controlled Trial; Social determinants of health; UK, United Kingdom; US, United States.

Figure 1

Selection of Included Studies - PRISMA Flow Diagram. A record refers to an entry in an electronic database describing a report. A report is a full text published research article and there may be one or more reports describing an individual research study. In this review, each report described a unique research study (n= 28 reports = 28 unique research studies).

Figure 2

Evidence for effectiveness of hospital-based preventative interventions for people experiencing homelessness by outcome category. This Harvest Plot is a ‘supermatrix’ covering eight categories of interventions and six categories of outcomes. Each bar represents one study and is annotated with the reference number. Bar colour indicates population with dark blue depicting exclusively homeless populations and light blue showing mixed homeless and other populations. Bar height indicates study quality rating: strong (highest), moderate (medium), weak (lowest). Bar pattern indicates setting with stripes representing emergency departments exclusively, solid bars representing inpatients exclusively, and spotted bars representing both emergency and inpatient settings. *Notes: HC = Healthcare; Feasibility = Feasibility, Acceptability and Engagement.