Identifying Undiagnosed High-Risk Suicidality Cases by Matching Patients With a Similar Comorbidity Burden: Retrospective Observational Study
Bibliographic record
Abstract
BACKGROUND: Suicide is the second leading cause of death for children and adolescents aged 6 to 18 years old. Pediatric suicidality is underreported, which poses significant challenges for effective intervention and prevention strategies. Identifying populations at risk for suicidality can provide critical benefits in terms of study cohort selection, prevalence estimation, and clinical resource allocation. OBJECTIVE: 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 patients with similar mental health comorbidity burden. METHODS: Electronic health record data from a large academic pediatric hospital in Boston, Massachusetts, were analyzed for patients aged 6-18 years old presenting to the emergency department between June 1, 2016, and June 1, 2022. Suicidality cases were defined using ICD-10 codes for three 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. Accuracy of the PSM model was validated against chart review by two independent subject matter experts. RESULTS: In total, 2,638 ED encounters met an ICD-10-based case definition of suicidality during the study period. The prevalence of suicidality (2.9%) by subtype was ideation (2.5%), self-harm (1.1%), and attempt (0.2%). Suicidality prevalence was more common for female sex (4.2%) than male sex (1.7%). Comorbidities of suicidality were statistically significant for 55 frequently co-occurring ICD-10 codes. Nearly half of these comorbidities (26/55) were not present in DSM-5, and nearly a quarter (12/55) consisted of ICD-10 codes for accidental rather than intentional self-harm. Increased probability of suicidality was observed for patients with personality disorder (44%), gender dysphoria (43%), bipolar disorder (36%), depression (33%), and schizophrenia spectrum disorders (32%). Based on gold standard chart review, 53.4% of propensity matched non-cases were unrecognized suicidality cases. CONCLUSIONS: Propensity score matching using comorbidity profiles is an effective approach for identifying suicidality cases that lack ICD-10 codes for suicidality.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".