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

Overview

Journal Acad Pediatr

Publisher Elsevier

Date 2023 Aug 31

PMID 37652162

Authors

May Shum

Allen Hsiao

Wei Teng

Andrea Asnes

Joshua Amrhein

Gunjan Tiyyagura

Affiliations

Soon will be listed here.

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.

Citing Articles

Fostering Tomorrow: Uniting Artificial Intelligence and Social Pediatrics for Comprehensive Child Well-being.

Gulsen M, Yalcin S Turk Arch Pediatr. 2024; 59(4):345-352.

PMID: 39110287 PMC: 11332429. DOI: 10.5152/TurkArchPediatr.2024.24076.

Developing and Testing the Usability of a Novel Child Abuse Clinical Decision Support System: Mixed Methods Study.

Thomas A, Asnes A, Libby K, Hsiao A, Tiyyagura G J Med Internet Res. 2024; 26():e51058.

PMID: 38551639 PMC: 11015363. DOI: 10.2196/51058.

References

Tiyyagura G, Asnes A, Leventhal J, Shapiro E, Auerbach M, Teng W . Development and Validation of a Natural Language Processing Tool to Identify Injuries in Infants Associated With Abuse. Acad Pediatr. 2021; 22(6):981-988. PMC: 9095755. DOI: 10.1016/j.acap.2021.11.004. View

Shum M, Asnes A, Leventhal J, Gaither J, Bechtel K, Powers E . The impact of a child abuse guideline on differences between pediatric and community emergency departments in the evaluation of injuries. Child Abuse Negl. 2021; 122:105374. DOI: 10.1016/j.chiabu.2021.105374. View

Flaherty E, Perez-Rossello J, Levine M, Hennrikus W . Evaluating children with fractures for child physical abuse. Pediatrics. 2014; 133(2):e477-89. DOI: 10.1542/peds.2013-3793. View

Olakotan O, Yusof M . Evaluating the alert appropriateness of clinical decision support systems in supporting clinical workflow. J Biomed Inform. 2020; 106:103453. DOI: 10.1016/j.jbi.2020.103453. View

Shum M, Asnes A, Leventhal J, Bechtel K, Gaither J, Tiyyagura G . The Use of Experts to Evaluate a Child Abuse Guideline in Community Emergency Departments. Acad Pediatr. 2020; 21(3):521-528. DOI: 10.1016/j.acap.2020.11.001. View

Harper N, Feldman K, Sugar N, Anderst J, Lindberg D . Additional injuries in young infants with concern for abuse and apparently isolated bruises. J Pediatr. 2014; 165(2):383-388.e1. DOI: 10.1016/j.jpeds.2014.04.004. View

Petska H, Sheets L . Sentinel injuries: subtle findings of physical abuse. Pediatr Clin North Am. 2014; 61(5):923-35. DOI: 10.1016/j.pcl.2014.06.007. View

Wood J, Hall M, Schilling S, Keren R, Mitra N, Rubin D . Disparities in the evaluation and diagnosis of abuse among infants with traumatic brain injury. Pediatrics. 2010; 126(3):408-14. DOI: 10.1542/peds.2010-0031. View

Berger R, Saladino R, Fromkin J, Heineman E, Suresh S, McGinn T . Development of an electronic medical record-based child physical abuse alert system. J Am Med Inform Assoc. 2017; 25(2):142-149. PMC: 7647132. DOI: 10.1093/jamia/ocx063. View

10.

Hymel K, Laskey A, Crowell K, Wang M, Armijo-Garcia V, Frazier T . Racial and Ethnic Disparities and Bias in the Evaluation and Reporting of Abusive Head Trauma. J Pediatr. 2018; 198:137-143.e1. PMC: 7243470. DOI: 10.1016/j.jpeds.2018.01.048. View

11.

Rasooly I, Khan A, Aldana Sierra M, Shankar M, Dang K, Cao L . Validating Use of ICD-10 Diagnosis Codes in Identifying Physical Abuse Among Young Children. Acad Pediatr. 2022; 23(2):396-401. PMC: 10228836. DOI: 10.1016/j.acap.2022.06.011. View

12.

Christian C . The evaluation of suspected child physical abuse. Pediatrics. 2015; 135(5):e1337-54. DOI: 10.1542/peds.2015-0356. View

13.

Rosenthal B, Skrbin J, Fromkin J, Heineman E, McGinn T, Richichi R . Integration of physical abuse clinical decision support at 2 general emergency departments. J Am Med Inform Assoc. 2019; 26(10):1020-1029. PMC: 7647214. DOI: 10.1093/jamia/ocz069. View

14.

Suresh S, Heineman E, Meyer L, Richichi R, Conger S, Young S . Improved Detection of Child Maltreatment with Routine Screening in a Tertiary Care Pediatric Hospital. J Pediatr. 2021; 243:181-187.e2. DOI: 10.1016/j.jpeds.2021.11.073. View

15.

Suresh S, Barata I, Feldstein D, Heineman E, Lindberg D, Bimber T . Clinical Decision Support for Child Abuse: Recommendations from a Consensus Conference. J Pediatr. 2022; 252:213-218.e5. DOI: 10.1016/j.jpeds.2022.06.039. View

16.

Pierce M, Kaczor K, Lorenz D, Bertocci G, Fingarson A, Makoroff K . Validation of a Clinical Decision Rule to Predict Abuse in Young Children Based on Bruising Characteristics. JAMA Netw Open. 2021; 4(4):e215832. PMC: 8047759. DOI: 10.1001/jamanetworkopen.2021.5832. View

17.

Lee S, Mohr N, Street W, Nadkarni P . Machine Learning in Relation to Emergency Medicine Clinical and Operational Scenarios: An Overview. West J Emerg Med. 2019; 20(2):219-227. PMC: 6404711. DOI: 10.5811/westjem.2019.1.41244. View

18.

Hooft A, Asnes A, Livingston N, Deutsch S, Cahill L, Wood J . The Accuracy of ICD Codes: Identifying Physical Abuse in 4 Children's Hospitals. Acad Pediatr. 2015; 15(4):444-50. PMC: 4739866. DOI: 10.1016/j.acap.2015.01.008. View

19.

Demner-Fushman D, Chapman W, McDonald C . What can natural language processing do for clinical decision support?. J Biomed Inform. 2009; 42(5):760-72. PMC: 2757540. DOI: 10.1016/j.jbi.2009.08.007. View

20.

Tiyyagura G, Asnes A, Leventhal J . Improving Child Abuse Recognition and Management: Moving Forward with Clinical Decision Support. J Pediatr. 2022; 252:11-13. DOI: 10.1016/j.jpeds.2022.08.020. View