EUVIMEDEUVIMED entdecken
Open Access

Detecting Pediatric Emergency Service Use for Suicide and Self-Harm: Multimodal Analysis of 3828 Encounters

Juliet Beni Edgcomb, Angshuman Saha, Alexandra Klomhaus, Elyse Tascione, Chrislie G Ponce, Joshua J Lee, Theona Tacorda, Bonnie T Zima

JMIR Mental Health · 2026

DOI: 10.2196/82371 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JMIR Mental Health, 2026. Verfasst von Juliet Beni Edgcomb und 7 weiteren Autor:innen. Beteiligte Einrichtung: Mental Health Informatics and Data Science (MINDS) Hub, Semel Institute for Neuroscience and Human Behavior, University of California, Los Angeles, 7…. Hauptthemen laut MEDLINE: Self-Injurious Behavior, Emergency Service, Hospital, Suicide. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIMH NIH HHS, NCATS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Suicide is the second-leading cause of US childhood mortality after 9 years of age. The accurate measurement of pediatric emergency service use for self-injurious thoughts and behaviors (SITB) remains challenging, as diagnostic codes undercount children. This measurement gap impedes public health and prevention efforts. Current research has not established which combination of electronic health record data elements achieves both high detection accuracy and consistent performance across youth populations.

Objective

This study aims to (1) compare the detection accuracy of electronic health record−based methods for identifying SITB-related pediatric emergency department (ED) visits: basic structured data ( International Classification of Diseases Version 10, Clinical Modification codes, chief concern), comprehensive structured data, clinical note text with natural language processing, and hybrid approaches combining structured data with notes; and (2) for each method, measure variability in detection by youth demographics and underlying mental health diagnosis.

Methods

Multiple human experts reviewed clinical records of 3828 pediatric mental health emergency visits (28,861 clinical notes) to a large health system with 2 EDs (June 2022-October 2024). The reviewers used the Columbia Classification Algorithm for Suicide Assessment to label the presence of SITB at the visit. Random forest classifiers were developed using 3 data modalities: (1) structured data (low-dimensional [International Classification of Diseases codes and chief concerns], medium-dimensional [adding Columbia Suicide Severity Rating Scale screening or mental health diagnoses], and high-dimensional [all structured data or augmented case surveillance, aCS]); (2) text data (general-purpose natural language processing, medical text-specific trained natural language processing, and Large Language Model Meta AI−derived scores), and (3) hybrid data (combining aCS with each text approach). Model performance was evaluated using area under the receiver operating characteristic curve (AUROC).

Results

Of the 3828 visits, 1760 (n=1760, 46.0%) were SITB-related. Detection performance improved with dimensionality: low-dimensional (AUROC=0.865), medium-dimensional (AUROC=0.934‐0.935), and high-dimensional (AUROC=0.965). Low-dimensional structured (International Classification of Diseases codes and chief concerns) showed high variability in detection, with lower accuracy among preadolescents (AUROC=0.821 vs 0.880 for adolescents); male participants (AUROC=0.817 vs 0.902 for females); and patients with neurodevelopmental (AUROC=0.568‐0.809), psychotic (AUROC=0.718), and disruptive disorders (AUROC=0.703). Hybrid modality (aCS+Large Language Model Meta AI) achieved optimal performance (AUROC=0.977), with AUROC ≥0.90 for all 20 demographic and 12/15 diagnostic subgroups.

Conclusions

This cross-sectional retrospective study identified that, relative to diagnostic codes and chief concern alone, hybrid structured-text detection methods improved accuracy and mitigated unwanted detection variability. The findings offer a scaffold for future clinical deployment of improved information retrieval of pediatric suicide and self-harm−related emergencies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Self-Injurious BehaviorEmergency Service, HospitalSuicideHumansChildMaleAdolescentFemaleElectronic Health RecordsEmergency Room VisitsNatural Language Processing

Stichwörter der Autor:innen

childrenclassification algorithmselectronic medical recordsemergency servicesmental disordersnatural language processing.text classification

Autor:innen und Institutionen

  • Mental Health Informatics and Data Science (MINDS) Hub, Semel Institute for Neuroscience and Human Behavior, University of California, Los Angeles, 760 Westwood Plz, Los Angeles, CA, 90095, United States, 1 310-825-9989.
  • Department of Medicine Statistics Core, David Geffen School of Medicine, University of California, Los Angeles, Los Angeles, CA, United States.
  • Biomedical Informatics Program, Clinical and Translational Science Institute, University of California, Los Angeles, Los Angeles, CA, United States.

Förderung

  • NIMH NIH HHS
  • NCATS NIH HHS

Zitieren

APA

Edgcomb, J. B., Saha, A., Klomhaus, A., Tascione, E., Ponce, C. G., Lee, J. J., Tacorda, T., & Zima, B. T. (2026). Detecting Pediatric Emergency Service Use for Suicide and Self-Harm: Multimodal Analysis of 3828 Encounters. JMIR Mental Health. https://doi.org/10.2196/82371

Vancouver

Edgcomb JB, Saha A, Klomhaus A, Tascione E, Ponce CG, Lee JJ, et al. Detecting Pediatric Emergency Service Use for Suicide and Self-Harm: Multimodal Analysis of 3828 Encounters. JMIR Mental Health. 2026. doi:10.2196/82371

BibTeX
@article{Edgcomb2026,
  author = {Edgcomb, Juliet Beni and Saha, Angshuman and Klomhaus, Alexandra and Tascione, Elyse and Ponce, Chrislie G and Lee, Joshua J and Tacorda, Theona and Zima, Bonnie T},
  title = {Detecting Pediatric Emergency Service Use for Suicide and Self-Harm: Multimodal Analysis of 3828 Encounters},
  journal = {JMIR Mental Health},
  year = {2026},
  doi = {10.2196/82371}
}
Kostenlos starten →