AutoPEWS: Automating Pediatric Early Warning Score Calculation Improves Accuracy Without Sacrificing Predictive Ability.
Journal
Pediatric quality & safety
ISSN: 2472-0054
Titre abrégé: Pediatr Qual Saf
Pays: United States
ID NLM: 101702480
Informations de publication
Date de publication:
Historique:
received:
10
10
2019
accepted:
22
02
2020
entrez:
20
5
2020
pubmed:
20
5
2020
medline:
20
5
2020
Statut:
epublish
Résumé
Pediatric early warning scores (PEWS) identify hospitalized children at risk for deterioration. Manual calculation is prone to human error. Electronic health records (EHRs) enable automated calculation, removing human error. This study's objective was to compare the accuracy of automated EHR-based PEWS calculation (AutoPEWS) to manual calculation and evaluate the non-inferiority of AutoPEWS in predicting deterioration. We performed a retrospective cohort study inclusive of non-intensive care unit inpatients at a freestanding children's hospital over 4.5 months in Fall 2018. AutoPEWS mapped the historical manual PEWS scoring rubric to frequently used EHR documentation. We determined accuracy by comparing the expected respiratory subset score based on the current respiratory rate to the actual respiratory score of AutoPEWS and the manual PEWS. The agreement was determined using kappa statistics. We used predicted probabilities from a generalized linear mixed model to calculate areas under the curve for each combination of scores (AutoPEWS, manual) and deterioration outcome (rapid response team activation, unplanned intensive care unit transfer, critical deterioration event). We compared the adjusted difference in areas under the curves between the scores. Non-inferiority was defined as a difference of <0.05. There were 23,514 total PEWS representative of 5,384 patients. AutoPEWS respiratory scores were 99.97% accurate, while the manual PEWS respiratory scores were 86% accurate. AutoPEWS were higher overall than the manual PEWS (mean 0.65 versus 0.34). They showed a fair-to-good agreement (weighted kappa 0.42). Non-inferiority of AutoPEWS compared with the manual PEWS was demonstrated for all deterioration outcomes. Automation of PEWS calculation improved accuracy without sacrificing predictive ability.
Identifiants
pubmed: 32426639
doi: 10.1097/pq9.0000000000000274
pmc: PMC7190249
doi:
Types de publication
Journal Article
Langues
eng
Pagination
e274Informations de copyright
Copyright © 2020 the Author(s). Published by Wolters Kluwer Health, Inc.
Références
Comput Inform Nurs. 2018 Jul;36(7):323-330
pubmed: 29990313
Paediatr Nurs. 2005 Feb;17(1):32-5
pubmed: 15751446
J Nurs Care Qual. 2014 Jul-Sep;29(3):215-22
pubmed: 24569518
Pediatrics. 2012 Apr;129(4):e874-81
pubmed: 22392182
Resuscitation. 2016 Dec;109:87-109
pubmed: 27496259
Pediatrics. 2013 May;131(5):e1563-75
pubmed: 23589808
BMJ Open. 2019 May 5;9(5):e022105
pubmed: 31061010
BMJ Qual Saf. 2013 Sep;22(9):719-26
pubmed: 23603474
Acad Pediatr. 2013 May-Jun;13(3):259-63
pubmed: 23680343
BMJ Open. 2017 Mar 13;7(3):e014497
pubmed: 28289051
Arch Dis Child. 2017 Jun;102(6):487-495
pubmed: 28292743
Resuscitation. 2006 Aug;70(2):173-8
pubmed: 16806641
Intensive Care Med. 2007 Apr;33(4):619-24
pubmed: 17235508
Acad Med. 2014 Jun;89(6):876-84
pubmed: 24871238
Br J Nurs. 2009 Jan 8-21;18(1):18-24
pubmed: 19127227
Lancet. 2011 Mar 19;377(9770):1011-8
pubmed: 21411136
Pediatrics. 2013 Apr;131(4):e1150-7
pubmed: 23478871
Comput Inform Nurs. 2017 May;35(5):228-236
pubmed: 27832032
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Open Med. 2014 May 06;8(2):e67-72
pubmed: 25009686