Identifying Undiagnosed High-Risk Suicidality Cases by Matching Patients With a Similar Comorbidity Burden: Retrospective Observational Study

TL;DR

This study uses health records to find children and teens at high risk of suicide by matching them with others who have similar mental health issues.

Contribution

A novel method using comorbidity profiles and propensity score matching to identify undiagnosed high-risk suicidality cases in pediatric emergency department patients.

Findings

2.9% of emergency department encounters involved suicidality, with higher rates in females.

53.4% of non-suicidality cases matched by comorbidity were later confirmed as undiagnosed suicidality cases.

Common comorbidities included depression, bipolar disorder, and personality disorders.

Abstract

Suicide is the second leading cause of death for children and adolescents aged 6 to 18 years. Pediatric suicidality is underreported, which poses significant challenges for effective intervention and prevention strategies. Identifying populations at risk of suicidality can provide critical benefits in terms of study cohort selection, prevalence estimation, and clinical resource allocation.

This study sought to (1) measure the prevalence of mental health comorbidities in pediatric suicidality and (2) identify undiagnosed high-risk suicidality cases by matching them with patients with a similar mental health comorbidity burden.

Electronic health record data from a large academic pediatric hospital in Boston, Massachusetts, were analyzed for patients aged 6 to 18 years presenting to the emergency department between June 1, 2016, and June 1, 2022. Suicidality cases were defined using International Classification of Diseases, 10th Revision (ICD-10) codes for 3 suicidality subtypes: suicidal ideation, self-harm, and suicide attempt. Comorbidities of suicidality were calculated as the conditional probability of ICD-10 code pairs. After multiple hypothesis corrections, statistically significant comorbidities and patient encounter demographics were input as covariates into a propensity score matching (PSM) model. The accuracy of the PSM model was validated against chart review by 2 independent subject matter experts.

In total, 2.9% (2638/90,980) of emergency department encounters met an ICD-10–based case definition of suicidality during the study period. The prevalence of suicidality by subtype was 2.5% (2275/90,980) for ideation, 1.1% (1030/90,980) for self-harm, and 0.2% (177/90,980) for suicide attempt. Suicidality prevalence was more common for the female sex (1825/43,929, 4.2%) than for the male sex (813/47,045, 1.7%). Comorbidities of suicidality were statistically significant for 55 frequently co-occurring ICD-10 codes. Nearly half of these comorbidities (26/55, 47.3%) were not present in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, and nearly a quarter (12/55, 21.8%) consisted of ICD-10 codes for accidental rather than intentional self-harm. Increased probability of suicidality was observed for patients with personality disorder (84/190, 44.2%), gender dysphoria (143/333, 42.9%), bipolar disorder (162/448, 36.2%), depression (1791/5426, 33%), and schizophrenia spectrum disorders (133/411, 32.4%). On the basis of gold-standard chart review, 53.4% of propensity-matched noncases were unrecognized cases of suicidality.

PSM using comorbidity profiles is an effective approach for identifying suicidality cases that lack ICD-10 codes for suicidality.

Figures