Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Jan-Feb;24(1):92-96.
doi: 10.1016/j.acap.2023.08.015. Epub 2023 Aug 29.

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

May Shum  1 , Allen Hsiao  2 , Wei Teng  3 , Andrea Asnes  2 , Joshua Amrhein  4 , Gunjan Tiyyagura  2
Affiliations

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

May Shum et al. Acad Pediatr. 2024 Jan-Feb.

Abstract

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.

Keywords: bias; child protection team; clinical decision support; guideline adherence; natural language processing.

PubMed Disclaimer

Conflict of interest statement

Declaration of Competing Interest The authors report no financial or ethical conflicts of interest. There are no prior publications or submissions with any overlapping information, including studies and patients.

Figures

Figure 1.
Figure 1.
Flow chart of inclusion criteria. aIn 12 encounters, we were unable to reproduce and determine the error due to iterative changes to the algorithm during the study period. bFor example, dermal melanocytosis initially documented as bruising; bruising caused by phlebotomy in the ED; and injuries found to be due to known birth trauma during the ED encounter.
See this image and copyright information in PMC

References

    1. U.S. Department of Health & Human Services AfCaF, Administration on Children, Youth and Families, Children’s Bureau. Child Maltreatment 2020. 2022.
    1. Ravichandiran N, Schuh S, Bejuk M, et al. Delayed identification of pediatric abuse-related fractures. Pediatrics. 2010;125:60–66. - PubMed
    1. Wood JN, Hall M, Schilling S, Keren R, Mitra N, Rubin DM. Disparities in the evaluation and diagnosis of abuse among infants with traumatic brain injury. Pediatrics. 2010;126:408–414. - PubMed
    1. Hymel KP, Laskey AL, Crowell KR, et al. Racial and Ethnic Disparities and Bias in the Evaluation and Reporting of Abusive Head Trauma. J Pediatr. 2018;198:137–143.e131. - PMC - PubMed
    1. Suresh S, Barata I, Feldstein D, et al. Clinical Decision Support for Child Abuse: Recommendations from a Consensus Conference. J Pediatr. 2022. - PubMed

Publication types