EUVIMEDEUVIMED entdecken
Open Access

Natural Language Processing — A Surveillance Stepping Stone to Identify Child Abuse

May Shum, Allen Hsiao, Wei Teng, Andrea Asnes, Joshua Amrhein, Gunjan Tiyyagura

Academic Pediatrics · 2024

DOI: 10.1016/j.acap.2023.08.015 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Academic Pediatrics, 2024. Verfasst von May Shum und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pediatrics (M Shum, A Hsiao, A Asnes, and G Tiyyagura), Yale University School of Medicine, New Haven, Conn. Electronic address: shumm@…. Hauptthemen laut MEDLINE: Child Abuse, Decision Support Systems, Clinical. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 24 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NICHD NIH HHS, NCATS NIH HHS, National Institute of Child Health and Human Development.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVE: We aimed to refine a natural language processing (NLP) algorithm that identified injuries associated with child abuse and identify areas in which integration into a real-time clinical decision support (CDS) tool may improve clinical care. METHODS: We applied an NLP algorithm in "silent mode" to all emergency department (ED) provider notes between July 2021 and December 2022 (n = 353) at 1 pediatric and 8 general EDs. We refined triggers for the NLP, assessed adherence to clinical guidelines, and evaluated disparities in degree of evaluation by examining associations between demographic variables and abuse evaluation or reporting to child protective services. RESULTS: Seventy-three cases falsely triggered the NLP, often due to errors in interpreting linguistic context. We identified common false-positive scenarios and refined the algorithm to improve NLP specificity. Adherence to recommended evaluation standards for injuries defined by nationally accepted clinical guidelines was 63%. There were significant demographic differences in evaluation and reporting based on presenting ED type, insurance status, and race and ethnicity. CONCLUSIONS: Analysis of an NLP algorithm in "silent mode" allowed for refinement of the algorithm and highlighted areas in which real-time CDS may help ED providers identify and pursue appropriate evaluation of injuries associated with child physical abuse.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Child AbuseDecision Support Systems, ClinicalHumansChildNatural Language ProcessingAlgorithmsEmergency Service, HospitalElectronic Health Records

Stichwörter der Autor:innen

biaschild protection teamclinical decision supportguideline adherencenatural language processing

Autor:innen und Institutionen

  • Department of Pediatrics (M Shum, A Hsiao, A Asnes, and G Tiyyagura), Yale University School of Medicine, New Haven, Conn. Electronic address: shumm@chop.edu.
  • Department of Pediatrics (M Shum, A Hsiao, A Asnes, and G Tiyyagura), Yale University School of Medicine, New Haven, Conn.
  • Yale New Haven Hospital (W Teng), Joint Data Analytics Team, Conn.
  • 3M Health Information Systems (J Amrhein), Implementation/Adoption Services, Pittsburgh, Pa.

Förderung

  • NICHD NIH HHS
  • NCATS NIH HHS
  • National Institute of Child Health and Human Development
  • National Institutes of Health

Zitieren

APA

Shum, M., Hsiao, A., Teng, W., Asnes, A., Amrhein, J., & Tiyyagura, G. (2024). Natural Language Processing — A Surveillance Stepping Stone to Identify Child Abuse. Academic Pediatrics. https://doi.org/10.1016/j.acap.2023.08.015

Vancouver

Shum M, Hsiao A, Teng W, Asnes A, Amrhein J, Tiyyagura G. Natural Language Processing — A Surveillance Stepping Stone to Identify Child Abuse. Academic Pediatrics. 2024. doi:10.1016/j.acap.2023.08.015

BibTeX
@article{Shum2024,
  author = {Shum, May and Hsiao, Allen and Teng, Wei and Asnes, Andrea and Amrhein, Joshua and Tiyyagura, Gunjan},
  title = {Natural Language Processing — A Surveillance Stepping Stone to Identify Child Abuse},
  journal = {Academic Pediatrics},
  year = {2024},
  doi = {10.1016/j.acap.2023.08.015}
}
Kostenlos starten →