Predicting oxygen requirements in patients with coronavirus disease 2019 using an artificial intelligence-clinician model based on local non-image data.
COVID-19
artificial intelligence-human collaboration
clinical practice
oxygen needs
sodium chloride difference
Journal
Frontiers in medicine
ISSN: 2296-858X
Titre abrégé: Front Med (Lausanne)
Pays: Switzerland
ID NLM: 101648047
Informations de publication
Date de publication:
2022
2022
Historique:
received:
12
09
2022
accepted:
14
11
2022
entrez:
19
12
2022
pubmed:
20
12
2022
medline:
20
12
2022
Statut:
epublish
Résumé
When facing unprecedented emergencies such as the coronavirus disease 2019 (COVID-19) pandemic, a predictive artificial intelligence (AI) model with real-time customized designs can be helpful for clinical decision-making support in constantly changing environments. We created models and compared the performance of AI in collaboration with a clinician and that of AI alone to predict the need for supplemental oxygen based on local, non-image data of patients with COVID-19. We enrolled 30 patients with COVID-19 who were aged >60 years on admission and not treated with oxygen therapy between December 1, 2020 and January 4, 2021 in this 50-bed, single-center retrospective cohort study. The outcome was requirement for oxygen after admission. The model performance to predict the need for oxygen by AI in collaboration with a clinician was better than that by AI alone. Sodium chloride difference >33.5 emerged as a novel indicator to predict the need for oxygen in patients with COVID-19. To prevent severe COVID-19 in older patients, dehydration compensation may be considered in pre-hospitalization care. In clinical practice, our approach enables the building of a better predictive model with prompt clinician feedback even in new scenarios. These can be applied not only to current and future pandemic situations but also to other diseases within the healthcare system.
Sections du résumé
Background
UNASSIGNED
When facing unprecedented emergencies such as the coronavirus disease 2019 (COVID-19) pandemic, a predictive artificial intelligence (AI) model with real-time customized designs can be helpful for clinical decision-making support in constantly changing environments. We created models and compared the performance of AI in collaboration with a clinician and that of AI alone to predict the need for supplemental oxygen based on local, non-image data of patients with COVID-19.
Materials and methods
UNASSIGNED
We enrolled 30 patients with COVID-19 who were aged >60 years on admission and not treated with oxygen therapy between December 1, 2020 and January 4, 2021 in this 50-bed, single-center retrospective cohort study. The outcome was requirement for oxygen after admission.
Results
UNASSIGNED
The model performance to predict the need for oxygen by AI in collaboration with a clinician was better than that by AI alone. Sodium chloride difference >33.5 emerged as a novel indicator to predict the need for oxygen in patients with COVID-19. To prevent severe COVID-19 in older patients, dehydration compensation may be considered in pre-hospitalization care.
Conclusion
UNASSIGNED
In clinical practice, our approach enables the building of a better predictive model with prompt clinician feedback even in new scenarios. These can be applied not only to current and future pandemic situations but also to other diseases within the healthcare system.
Identifiants
pubmed: 36530899
doi: 10.3389/fmed.2022.1042067
pmc: PMC9748157
doi:
Types de publication
Journal Article
Langues
eng
Pagination
1042067Informations de copyright
Copyright © 2022 Muto, Fukuta, Watanabe, Shindo, Kanemitsu, Kajikawa, Yonezawa, Inoue, Ichihashi, Shiratori and Maruyama.
Déclaration de conflit d'intérêts
Authors SF and TW were employed by the company Fujitsu Limited. The remaining authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Références
J Am Med Inform Assoc. 2021 Mar 1;28(3):653-663
pubmed: 33325504
BMC Med. 2015 Jan 06;13:1
pubmed: 25563062
Radiology. 2020 Jan;294(1):199-209
pubmed: 31714194
Patient Saf Surg. 2019 Feb 1;13:6
pubmed: 30733829
Lancet Digit Health. 2021 Aug;3(8):e496-e506
pubmed: 34219054
J Nippon Med Sch. 2022 May 12;89(2):161-168
pubmed: 34526457
Cell Host Microbe. 2020 Jun 10;27(6):883-890.e2
pubmed: 32407669
Ann Emerg Med. 2004 Aug;44(2):108-13
pubmed: 15278081
Am J Surg Pathol. 2018 Dec;42(12):1636-1646
pubmed: 30312179
BMC Med Inform Decis Mak. 2018 Sep 4;18(1):78
pubmed: 30180839
Medicine (Baltimore). 2019 Oct;98(42):e17596
pubmed: 31626135
Front Immunol. 2021 Jan 29;11:607583
pubmed: 33584679
IEEE Trans Med Imaging. 2020 Apr;39(4):1184-1194
pubmed: 31603772
Lancet. 2022 Feb 12;399(10325):620
pubmed: 35151388
Comput Intell Neurosci. 2022 Apr 18;2022:6093613
pubmed: 35444694
J Biomed Inform. 2021 Jul;119:103802
pubmed: 33965640
JAMA Netw Open. 2021 Apr 1;4(4):e217249
pubmed: 33909055
Int J Gen Med. 2022 Oct 07;15:7701-7708
pubmed: 36238542
Nat Med. 2020 Aug;26(8):1229-1234
pubmed: 32572267
Med Biol Eng Comput. 2022 Apr;60(4):957-968
pubmed: 35147843
JAMA Netw Open. 2019 Jun 5;2(6):e195600
pubmed: 31173130
Am J Kidney Dis. 2017 May;69(5):707-708
pubmed: 28285873
J Biomed Inform. 2021 Jun;118:103794
pubmed: 33933654
NPJ Digit Med. 2020 Sep 9;3:115
pubmed: 32964138
BMJ. 2022 Feb 17;376:e068576
pubmed: 35177406
BMJ Open. 2021 Jun 15;11(6):e047007
pubmed: 34130961
Gerontology. 2022;68(9):1027-1037
pubmed: 34999588
Lancet Digit Health. 2020 Mar;2(3):e138-e148
pubmed: 33334578
NPJ Digit Med. 2020 Feb 26;3:23
pubmed: 32140566
Sensors (Basel). 2021 Nov 08;21(21):
pubmed: 34770722
Oncologist. 2019 Jun;24(6):772-782
pubmed: 30446581
J Biomed Inform. 2022 May;129:104028
pubmed: 35181495