Risk of suicide and repeat self-harm after hospital attendance for non-fatal self-harm in Sri Lanka: a cohort study

Abstract

Background: Evidence from high income countries (HICs) suggests that individuals who present to hospital after self-harm are an important target for suicide prevention, but evidence from low and middle-income countries (LMICs) is lacking. We aimed to investigate the risk of repeat self-harm and suicide, and factors associated with these outcomes, in a large cohort of patients presenting to hospital with self-harm in rural Sri Lanka.

Methods: In this cohort study, hospital presentations for self-harm at 13 hospitals in a rural area of North Central Province (population 224 000), Sri Lanka, were followed up with a self-harm surveillance system, established as part of a community randomised trial, and based on data from all hospitals, coroners, and police stations in the study area. We estimated the risk of repeat non-fatal and fatal self-harm and risk factors for repetition with Kaplan-Meier methods and Cox proportional hazard models. Sociodemographic (age, sex, and socioeconomic position) and clinical (past self-harm and method of self-harm) characteristics investigated were drawn from a household survey in the study area and data recorded at the time of index hospital presentation. We included all individuals who had complete data for all variables in the study in our primary analysis.

Outcomes: Between July 29, 2011, and May 12, 2016, we detected 3073 episodes of self-harm (fatal and non-fatal) in our surveillance system, of which 2532 (82·3%) were linked back to an individual in the baseline survey. After exclusion of 145 ineligible episodes, we analysed 2259 index episodes of self-harm. By use of survival models, the estimated risk of repeat self-harm (12 months: 3· 1%, 95% CI 2·4-3·9; 24 months: 5·2%, 4·3-6·4) and suicide (12 months: 0·6%, 0·4-1·1; 24 months: 0·8%, 0·5-1·3) in our study was considerably lower than that in HICs. A higher risk of repeat self-harm was observed in men than in women (fatal and non-fatal; hazard ratio 2·0, 95% CI 1·3-3·2; p=0·0021), in individuals aged 56 years and older compared with those aged 10-25 years (fatal; 16·1, 4·3-59·9; p=0·0027), and those who used methods other than poisoning in their index presentation (fatal and non-fatal; 3·9, 2·0-7·6; p=0·00027). We found no evidence of increased risk of repeat self-harm or suicide in those with a history of self-harm before the index episode.

Interpretation: Although people who self-harm are an important high-risk group, focusing suicide prevention efforts on those who self-harm might be somewhat less important in LMICs compared with HICs given the low risk of repeat self-harm and subsequent suicide death. Strategies that focus on other risk factors for suicide might be more effective in reducing suicide deaths in LMICs in south Asia. A better understanding of the low incidence of repeat self-harm is also needed, as this could contribute to prevention strategies in nations with a higher incidence of repetition and subsequent suicide death.

Funding: Wellcome Trust.

Figure 1

Cohort identification

Figure 2

Kaplan-Meier graph of time to the first non-fatal repeat episode of self-harm by sex