Meta-analysis of suicide rates in the first week and the first month after psychiatric hospitalisation

Abstract

Objective: To assess the magnitude of suicide rates in the first week and first month postdischarge following psychiatric hospitalisation.

Design: Meta-analysis of relevant English-language, peer-reviewed papers published in MEDLINE, PsycINFO or Embase between 01 January 1945 and 31 March 2017 and supplemented by hand searching and personal communication. A generalised linear effects model was fitted to the number of suicides, with a Poisson distribution, log link and log of person years as an offset. A random effects model was used to calculate the overall pooled rates and within subgroups in sensitivity analyses.

Outcome measures: Suicides per 100 000 person years in the first week and the first month after discharge from psychiatric hospitalisation.

Results: Thirty-four included papers comprised 29 studies that reported suicides in the first month postdischarge (3551 suicides during 222 546 patient years) and 24 studies that reported suicides in the first week postdischarge (1928 suicides during 60 880 patient years). The pooled estimate of the suicide rate in the first month postdischarge suicide was 2060 per 100 000 person years (95% CI=1300 to 3280, I²=90). The pooled estimate of the suicide rate in the first week postdischarge suicide was 2950 suicides per 100 000 person years (95% CI=1740 to 5000, I²=88). Eight studies that were included after personal communication had lower pooled rates of suicide than studies included after data extraction and there was evidence of publication bias towards papers reporting a higher rate of postdischarge suicide.

Conclusion: Acknowledging the presence of marked heterogeneity between studies and the likelihood of bias towards publication of studies reporting a higher postdischarge suicide rate, the first week and first month postdischarge following psychiatric hospitalisation are periods of extraordinary suicide risk. Short-term follow-up of discharged patients should be augmented with greater focus on safe transition from hospital to community care.

Prospero registration number: PROSPERO registration CRD42016038169.

Keywords: epidemiology; risk management.

Figure 1

Preferred Reporting Items for Systematic Reviews and Meta-Analyses flowchart.

Figure 2

Forest plot of suicide rates in 1 month following discharge from psychiatric hospitalisation.

Figure 3

Forest plot of suicide rates in 1 week following discharge from psychiatric hospitalisation.