Predicting neurological outcomes after in-hospital cardiac arrests for patients with Coronavirus Disease 2019.
Cardiac arrest
Machine learning
Neurological outcomes
Prediction
Journal
Resuscitation
ISSN: 1873-1570
Titre abrégé: Resuscitation
Pays: Ireland
ID NLM: 0332173
Informations de publication
Date de publication:
09 2022
09 2022
Historique:
received:
22
04
2022
revised:
13
07
2022
accepted:
14
07
2022
pubmed:
23
7
2022
medline:
17
8
2022
entrez:
22
7
2022
Statut:
ppublish
Résumé
Machine learning models are more accurate than standard tools for predicting neurological outcomes in patients resuscitated after cardiac arrest. However, their accuracy in patients with Coronavirus Disease 2019 (COVID-19) is unknown. Therefore, we compared their performance in a cohort of cardiac arrest patients with COVID-19. We conducted a retrospective analysis of resuscitation survivors in the Get With The Guidelines®-Resuscitation (GWTG-R) COVID-19 registry between February 2020 and May 2021. The primary outcome was a favorable neurological outcome, indicated by a discharge Cerebral Performance Category score ≤ 2. Pre- and peri-arrest variables were used as predictors. We applied our published logistic regression, neural network, and gradient boosted machine models developed in patients without COVID-19 to the COVID-19 cohort. We also updated the neural network model using transfer learning. Performance was compared between models and the Cardiac Arrest Survival Post-Resuscitation In-Hospital (CASPRI) score. Among the 4,125 patients with COVID-19 included in the analysis, 484 (12 %) patients survived with favorable neurological outcomes. The gradient boosted machine, trained on non-COVID-19 patients was the best performing model for predicting neurological outcomes in COVID-19 patients, significantly better than the CASPRI score (c-statistic: 0.75 vs 0.67, P < 0.001). While calibration improved for the neural network with transfer learning, it did not surpass the gradient boosted machine in terms of discrimination. Our gradient boosted machine model developed in non-COVID patients had high discrimination and adequate calibration in COVID-19 resuscitation survivors and may provide clinicians with important information for these patients.
Sections du résumé
BACKGROUND
Machine learning models are more accurate than standard tools for predicting neurological outcomes in patients resuscitated after cardiac arrest. However, their accuracy in patients with Coronavirus Disease 2019 (COVID-19) is unknown. Therefore, we compared their performance in a cohort of cardiac arrest patients with COVID-19.
METHODS
We conducted a retrospective analysis of resuscitation survivors in the Get With The Guidelines®-Resuscitation (GWTG-R) COVID-19 registry between February 2020 and May 2021. The primary outcome was a favorable neurological outcome, indicated by a discharge Cerebral Performance Category score ≤ 2. Pre- and peri-arrest variables were used as predictors. We applied our published logistic regression, neural network, and gradient boosted machine models developed in patients without COVID-19 to the COVID-19 cohort. We also updated the neural network model using transfer learning. Performance was compared between models and the Cardiac Arrest Survival Post-Resuscitation In-Hospital (CASPRI) score.
RESULTS
Among the 4,125 patients with COVID-19 included in the analysis, 484 (12 %) patients survived with favorable neurological outcomes. The gradient boosted machine, trained on non-COVID-19 patients was the best performing model for predicting neurological outcomes in COVID-19 patients, significantly better than the CASPRI score (c-statistic: 0.75 vs 0.67, P < 0.001). While calibration improved for the neural network with transfer learning, it did not surpass the gradient boosted machine in terms of discrimination.
CONCLUSION
Our gradient boosted machine model developed in non-COVID patients had high discrimination and adequate calibration in COVID-19 resuscitation survivors and may provide clinicians with important information for these patients.
Identifiants
pubmed: 35868590
pii: S0300-9572(22)00609-8
doi: 10.1016/j.resuscitation.2022.07.018
pmc: PMC9295318
pii:
doi:
Types de publication
Journal Article
Research Support, N.I.H., Extramural
Research Support, U.S. Gov't, Non-P.H.S.
Langues
eng
Sous-ensembles de citation
IM
Pagination
55-62Subventions
Organisme : NHLBI NIH HHS
ID : K01 HL148390
Pays : United States
Organisme : NIDDK NIH HHS
ID : R01 DK126933
Pays : United States
Organisme : NIGMS NIH HHS
ID : R01 GM123193
Pays : United States
Organisme : NHLBI NIH HHS
ID : R01 HL157262
Pays : United States
Informations de copyright
Copyright © 2022 Elsevier B.V. All rights reserved.
Références
Arch Intern Med. 2012 Jun 25;172(12):947-53
pubmed: 22641228
JAMA Intern Med. 2013 Nov 11;173(20):1872-8
pubmed: 24018585
J Gen Intern Med. 1998 Dec;13(12):805-16
pubmed: 9844078
Crit Care Explor. 2021 May 14;3(5):e0425
pubmed: 34036276
JAMA Intern Med. 2021 Feb 1;181(2):279-281
pubmed: 32986117
Eur Heart J. 2021 Mar 14;42(11):1094-1106
pubmed: 33543259
N Engl J Med. 2020 Apr 30;382(18):e41
pubmed: 32212516
Crit Care Med. 2021 Dec 1;49(12):e1196-e1205
pubmed: 34259450
Circulation. 2019 Aug 27;140(9):e517-e542
pubmed: 31291775
Crit Care Med. 2022 Feb 1;50(2):e162-e172
pubmed: 34406171
J Am Heart Assoc. 2021 Aug 17;10(16):e021204
pubmed: 34376062
BMJ. 2021 Mar 10;372:n436
pubmed: 33692022
N Engl J Med. 2012 Nov 15;367(20):1912-20
pubmed: 23150959
Resuscitation. 2015 Apr;89:86-92
pubmed: 25636896
Circulation. 2020 Jun 23;141(25):e933-e943
pubmed: 32270695
Resuscitation. 2021 Mar;160:72-78
pubmed: 33515638
Biometrics. 1988 Sep;44(3):837-45
pubmed: 3203132
Resuscitation. 2018 Nov;132:1-5
pubmed: 30138650
BMJ. 2020 Sep 30;371:m3513
pubmed: 32998872
JAMA. 2019 Mar 26;321(12):1200-1210
pubmed: 30912843