Risk of homelessness after prison release and recidivism in Denmark: a nationwide, register-based cohort study

Abstract

Background: Transitional periods between and across services have been linked to homelessness. We aimed to investigate the association of previous history of homelessness and psychiatric disorders with risk of homelessness after release from prison. Additionally, we examined the association between homelessness after release and risk of recidivism.

Methods: We did a nationwide, register-based cohort study of people aged 15 years or older who were released from prison for the first time in Denmark between Jan 1, 2001, and Dec 31, 2021. We obtained data using the Danish Civil Registration System with data linked across other registries (the Danish Central Criminal Register, the Danish Homeless Register, the Danish National Patient Register, and the Danish Psychiatric Central Research Register) on release date, homeless shelter contacts, psychiatric disorders, and new convictions. Outcomes were homelessness after release from prison, defined as first homeless shelter contact following release from first imprisonment, and recidivism within 2 years of release, defined as the first police-recorded criminal conviction after prison release. We calculated incidence rates per 1000 person-years, incidence rate ratios (IRRs) using Poisson regression analysis, and probability of homelessness and recidivism after release. Sex, age, calendar year, country of origin, highest educational level, relationship status, and length of index imprisonment were included as confounders.

Findings: The study cohort included 37 382 individuals (34 792 males [93·1%] and 2590 females [6·9%]) aged 15-41 years, who were released from prison between Jan 1, 2001, and Dec 31, 2021, contributing 202 197 person-years at risk. Mean follow-up duration was 5·4 person-years (SD 5·6). Overall, 1843 (4·9%) of 37 382 individuals became homeless. 1 year after release from prison, 788 (2·1%) of 37 382 individuals had at least one homeless shelter contact, and among 1761 individuals with previous history of homelessness before index imprisonment, 357 (20·7%) became homeless. The incidence of homelessness after release was 102·5 cases per 1000 person-years for individuals with previous history of homelessness and 6·7 cases per 1000 person-years in individuals without (IRR 16·4, 95% CI 14·8-18·2; adjusted for sex, age, and calendar year). Individuals who additionally had a mental illness had a higher risk of homelessness (IRR 22·6, 19·7-25·9) compared with those without either previous homelessness or mental illness, and a substantially higher risk was observed for those with previous homelessness and drug use disorder (25·0, 21·6-28·9) compared with those without. Within 2 years of release from prison, the probability of recidivism was 73·2% (95% CI 72·8-73·7). The risk of recidivism was higher among people experiencing homelessness after release from prison than those who did not experience homelessness after release (IRR 1·5, 95% CI 1·3-1·7), adjusted for sex, age, and calendar year.

Interpretation: Criminal justice services should review approaches to reduce risk of homelessness, and consider improving liaison with mental health and substance misuse services to prevent adverse outcomes on release from prison. Clinical guidelines applied to criminal justice settings should address the health of individuals who experience homelessness.

Funding: Lundbeck Foundation.

Figure 1. Probability of homelessness after first prison release, 2001–21

Probability of homelessness during one year after first prison release by sex (A) and by homelessness before index imprisonment (B). Competing risks from death, emigration, and second imprisonment were accounted for using the Aalen-Johansen estimator.

Figure 2. Homelessness after prison release, 2001–21

Risk of homelessness after first prison release by history of homelessness before index imprisonment, independent of, and in combination with, psychiatric disorders. Model 1 was adjusted for sex, age, and calendar time. Model 2 was additionally adjusted for country of origin, highest educational level, relationship status 1 year before release, and length of imprisonment. Error bars show 95% CIs. The dotted horizontal line shows the reference group (IRR=1) with no experiences of homelessness and without the individual psychiatric disorder examined. IRR=incidence rate ratio.

Figure 3. Probability of recidivism after first prison release, 2001–21

Probability of recidivism—ie, any police-recorded conviction, within 2 years of first prison release by sex. Competing risks from death and emigration were accounted for using the Aalen-Johansen estimator.

Figure 4. Recidivism after prison release, 2001–21

IRRs of recidivism within 2 years of first prison release by homelessness after release independent of, and in combination with, psychiatric disorders before index imprisonment. Model 1 was adjusted for sex, age, and calendar time. Model 2 was additionally adjusted for country of origin, highest educational level, relationship status 1 year before release, and length of index imprisonment. Error bars show 95% CIs. The dotted horizontal line shows the reference group (IRR=1) with no experiences of homelessness and without the individual psychiatric disorder examined. IRR=incidence rate ratio.