-
Tytuł:
-
Development and Validation of a Natural Language Processing Tool to Identify Injuries in Infants Associated With Abuse.
-
Autorzy:
-
Tiyyagura G; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT. Electronic address: .
Asnes AG; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Leventhal JM; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Shapiro ED; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Auerbach M; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Teng W; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Powers E; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Thomas A; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
Lindberg DM; University of Colorado Anschutz Medical Campus (DM Lindberg), Aurora Colo.
McClelland J; 3M | M*Modal Health Information Systems (J McClelland, C Kutryb, T Polzin, K Daughtridge, V Sevin), Pittsburg, Pa.
Kutryb C; 3M | M*Modal Health Information Systems (J McClelland, C Kutryb, T Polzin, K Daughtridge, V Sevin), Pittsburg, Pa.
Polzin T; 3M | M*Modal Health Information Systems (J McClelland, C Kutryb, T Polzin, K Daughtridge, V Sevin), Pittsburg, Pa.
Daughtridge K; 3M | M*Modal Health Information Systems (J McClelland, C Kutryb, T Polzin, K Daughtridge, V Sevin), Pittsburg, Pa.
Sevin V; 3M | M*Modal Health Information Systems (J McClelland, C Kutryb, T Polzin, K Daughtridge, V Sevin), Pittsburg, Pa.
Hsiao AL; Yale University School of Medicine (G Tiyyagura, AG Asnes, JM Leventhal, ED Shapiro, M Auerbach, W Teng, E Powers, A Thomas, AL Hsiao), New Haven, CT.
-
Źródło:
-
Academic pediatrics [Acad Pediatr] 2022 Aug; Vol. 22 (6), pp. 981-988. Date of Electronic Publication: 2021 Nov 12.
-
Typ publikacji:
-
Journal Article; Research Support, N.I.H., Extramural
-
Język:
-
English
-
Imprint Name(s):
-
Original Publication: New York : Elsevier
-
MeSH Terms:
-
Child Abuse*/diagnosis
Natural Language Processing*
Algorithms ; Child ; Electronic Health Records ; Humans ; Infant ; Sensitivity and Specificity
-
References:
-
J Am Med Inform Assoc. 2007 Jul-Aug;14(4):415-23. (PMID: 17460127)
Acad Pediatr. 2020 Jan - Feb;20(1):39-45. (PMID: 30880065)
J Emerg Med. 2019 Jun;56(6):592-600. (PMID: 30879856)
BMC Pulm Med. 2018 Feb 13;18(1):34. (PMID: 29439692)
Pediatrics. 2014 Feb;133(2):e477-89. (PMID: 24470642)
Pediatr Emerg Care. 2014 Nov;30(11):771-6. (PMID: 25343739)
Pediatrics. 2014 Jul;134(1):45-53. (PMID: 24935996)
Pediatrics. 2013 Apr;131(4):701-7. (PMID: 23478861)
Acad Emerg Med. 2021 Jan;28(1):70-81. (PMID: 32931628)
J Am Med Inform Assoc. 2018 Feb 1;25(2):142-149. (PMID: 28641385)
Burns. 2018 Mar;44(2):335-343. (PMID: 28918905)
Child Abuse Negl. 2019 Mar;89:70-77. (PMID: 30639971)
J Pediatr. 2018 Jul;198:137-143.e1. (PMID: 29606408)
Pediatrics. 2006 Mar;117(3):722-8. (PMID: 16510652)
Acad Emerg Med. 2016 May;23(5):628-36. (PMID: 26826020)
J Am Med Inform Assoc. 2019 Oct 1;26(10):1020-1029. (PMID: 31197358)
Child Abuse Negl. 2014 Jul;38(7):1275-81. (PMID: 24325939)
Pediatrics. 2015 May;135(5):e1337-54. (PMID: 25917988)
Pediatrics. 2015 Nov;136(5):831-8. (PMID: 26438705)
JAMA Netw Open. 2021 Apr 1;4(4):e215832. (PMID: 33852003)
AMIA Annu Symp Proc. 2007 Oct 11;:26-30. (PMID: 18693791)
West J Emerg Med. 2019 Mar;20(2):219-227. (PMID: 30881539)
Pediatrics. 2015 Feb;135(2):e312-20. (PMID: 25601982)
Evid Based Med. 2016 Dec;21(6):203-207. (PMID: 27664174)
Child Abuse Negl. 2018 Nov;85:58-67. (PMID: 30170921)
JAMA. 1999 Feb 17;281(7):621-6. (PMID: 10029123)
Pediatr Emerg Care. 2006 Apr;22(4):211-4. (PMID: 16651907)
J Pediatr Surg. 2009 Jun;44(6):1229-34; discussion 1234-5. (PMID: 19524746)
Acad Pediatr. 2021 Mar;21(2):221-222. (PMID: 32961336)
Neurology. 2017 Jan 10;88(2):164-168. (PMID: 27927935)
Pediatrics. 2012 Nov;130(5):853-60. (PMID: 23071208)
Pediatrics. 2010 Jan;125(1):60-6. (PMID: 19948569)
Pediatrics. 2012 Sep;130(3):457-64. (PMID: 22926179)
JAMA Pediatr. 2015 Jun;169(6):527-34. (PMID: 25867088)
-
Grant Information:
-
K12 RR017594 United States RR NCRR NIH HHS; T35 HL007649 United States HL NHLBI NIH HHS; UL1 TR001863 United States TR NCATS NIH HHS
-
Contributed Indexing:
-
Keywords: child abuse; emergency department; natural language processing; test characteristics
-
Entry Date(s):
-
Date Created: 20211115 Date Completed: 20220809 Latest Revision: 20230802
-
Update Code:
-
20240105
-
PubMed Central ID:
-
PMC9095755
-
DOI:
-
10.1016/j.acap.2021.11.004
-
PMID:
-
34780997
-
Objectives: Medically minor but clinically important findings associated with physical child abuse, such as bruises in pre-mobile infants, may be identified by frontline clinicians yet the association of these injuries with child abuse is often not recognized, potentially allowing the abuse to continue and even to escalate. An accurate natural language processing (NLP) algorithm to identify high-risk injuries in electronic health record notes could improve detection and awareness of abuse. The objectives were to: 1) develop an NLP algorithm that accurately identifies injuries in infants associated with abuse and 2) determine the accuracy of this algorithm.
Methods: An NLP algorithm was designed to identify ten specific injuries known to be associated with physical abuse in infants. Iterative cycles of review identified inaccurate triggers, and coding of the algorithm was adjusted. The optimized NLP algorithm was applied to emergency department (ED) providers' notes on 1344 consecutive sample of infants seen in 9 EDs over 3.5 months. Results were compared with review of the same notes conducted by a trained reviewer blind to the NLP results with discrepancies adjudicated by a child abuse expert.
Results: Among the 1344 encounters, 41 (3.1%) had one of the high-risk injuries. The NLP algorithm had a sensitivity and specificity of 92.7% (95% confidence interval [CI]: 79.0%-98.1%) and 98.1% (95% CI: 97.1%-98.7%), respectively, and positive and negative predictive values were 60.3% and 99.8%, respectively, for identifying high-risk injuries.
Conclusions: An NLP algorithm to identify infants with high-risk injuries in EDs has good accuracy and may be useful to aid clinicians in the identification of infants with injuries associated with child abuse.
(Copyright © 2021 Academic Pediatric Association. Published by Elsevier Inc. All rights reserved.)
