دورية أكاديمية
أعرض في EDS

Validation of a deep learning, value-based care model to predict mortality and comorbidities from chest radiographs in COVID-19.

التفاصيل البيبلوغرافية
العنوان: Validation of a deep learning, value-based care model to predict mortality and comorbidities from chest radiographs in COVID-19.
المؤلفون: Pyrros A; Department of Radiology, Duly Health and Care, Hinsdale, Illinois., Rodriguez Fernandez J; Department of Neurology, University of Illinois at Chicago, Chicago, Illinois., Borstelmann SM; Department of Radiology, University of Central Florida, Orlando, Florida., Flanders A; Department of Radiology, Thomas Jefferson University Hospital, Philadelphia, Pennsylvania., Wenzke D; Department of Radiology, NorthShore University HealthSystem, Evanston, Illinois., Hart E; Department of Radiology, Northwestern University, Chicago, Illinois., Horowitz JM; Department of Radiology, Northwestern University, Chicago, Illinois., Nikolaidis P; Department of Radiology, Northwestern University, Chicago, Illinois., Willis M; Department of Radiology, Duly Health and Care, Hinsdale, Illinois., Chen A; Department of Computer Science, University of Illinois at Urbana- Champaign, Urbana-Champaign, Illinois., Cole P; Department of Computer Science, University of Illinois at Urbana- Champaign, Urbana-Champaign, Illinois., Siddiqui N; Department of Radiology, Duly Health and Care, Hinsdale, Illinois., Muzaffar M; Department of Radiology, Duly Health and Care, Hinsdale, Illinois., Muzaffar N; Department of Radiology, Duly Health and Care, Hinsdale, Illinois., McVean J; Medtronic, Minneapolis, Minnesota., Menchaca M; Department of Radiology, University of Illinois at Chicago, Chicago, Illinois., Katsaggelos AK; Department of Electrical and Computer Engineering, Northwestern University, Evanston, Illinois., Koyejo S; Department of Computer Science, University of Illinois at Urbana- Champaign, Urbana-Champaign, Illinois., Galanter W; Department of Medicine, University of Illinois at Chicago, Chicago, Illinois.
المصدر: PLOS digital health [PLOS Digit Health] 2022 Aug 01; Vol. 1 (8), pp. e0000057. Date of Electronic Publication: 2022 Aug 01 (Print Publication: 2022).
نوع المنشور: Journal Article
اللغة: English
بيانات الدورية: Publisher: PLOS Country of Publication: United States NLM ID: 9918335064206676 Publication Model: eCollection Cited Medium: Internet ISSN: 2767-3170 (Electronic) Linking ISSN: 27673170 NLM ISO Abbreviation: PLOS Digit Health Subsets: PubMed not MEDLINE
أسماء مطبوعة: Original Publication: San Francisco, California : PLOS, [2022]-
مستخلص: We validate a deep learning model predicting comorbidities from frontal chest radiographs (CXRs) in patients with coronavirus disease 2019 (COVID-19) and compare the model's performance with hierarchical condition category (HCC) and mortality outcomes in COVID-19. The model was trained and tested on 14,121 ambulatory frontal CXRs from 2010 to 2019 at a single institution, modeling select comorbidities using the value-based Medicare Advantage HCC Risk Adjustment Model. Sex, age, HCC codes, and risk adjustment factor (RAF) score were used. The model was validated on frontal CXRs from 413 ambulatory patients with COVID-19 (internal cohort) and on initial frontal CXRs from 487 COVID-19 hospitalized patients (external cohort). The discriminatory ability of the model was assessed using receiver operating characteristic (ROC) curves compared to the HCC data from electronic health records, and predicted age and RAF score were compared using correlation coefficient and absolute mean error. The model predictions were used as covariables in logistic regression models to evaluate the prediction of mortality in the external cohort. Predicted comorbidities from frontal CXRs, including diabetes with chronic complications, obesity, congestive heart failure, arrhythmias, vascular disease, and chronic obstructive pulmonary disease, had a total area under ROC curve (AUC) of 0.85 (95% CI: 0.85-0.86). The ROC AUC of predicted mortality for the model was 0.84 (95% CI,0.79-0.88) for the combined cohorts. This model using only frontal CXRs predicted select comorbidities and RAF score in both internal ambulatory and external hospitalized COVID-19 cohorts and was discriminatory of mortality, supporting its potential use in clinical decision making.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2022 Pyrros et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
References: JAMA Netw Open. 2019 Jul 3;2(7):e197416. (PMID: 31322692)
Am J Manag Care. 2017 Feb 1;23(2):e41-e49. (PMID: 28245661)
J Am Coll Radiol. 2022 Jan;19(1 Pt B):184-191. (PMID: 35033309)
J Clin Epidemiol. 2003 Mar;56(3):221-9. (PMID: 12725876)
JAMA. 2020 May 26;323(20):2052-2059. (PMID: 32320003)
Emerg Radiol. 2020 Dec;27(6):617-621. (PMID: 32572707)
Radiology. 2021 Jan;298(1):E46-E54. (PMID: 32787701)
BMJ. 2020 Apr 7;369:m1328. (PMID: 32265220)
Radiology. 2021 Mar;298(3):486-491. (PMID: 33346696)
Int J Infect Dis. 2020 May;94:91-95. (PMID: 32173574)
J Am Geriatr Soc. 2009 Dec;57(12):2306-10. (PMID: 19874405)
Med Princ Pract. 2019;28(2):133-140. (PMID: 30481749)
Radiology. 2017 Feb;282(2):333-347. (PMID: 28099106)
Nature. 2020 Aug;584(7821):430-436. (PMID: 32640463)
Radiology. 2022 Jul;304(1):85-95. (PMID: 35380492)
JAMA Intern Med. 2017 Sep 1;177(9):1295-1296. (PMID: 28692717)
J Stroke. 2013 May;15(2):122-5. (PMID: 24324948)
PLoS One. 2020 Nov 11;15(11):e0241825. (PMID: 33175863)
Eur Respir J. 2020 Dec 24;56(6):. (PMID: 32978307)
Lancet. 2020 Feb 15;395(10223):497-506. (PMID: 31986264)
Int J Integr Care. 2016 Oct 26;16(4):4. (PMID: 28316544)
Biometrics. 1988 Sep;44(3):837-45. (PMID: 3203132)
Radiology. 2020 Oct;297(1):E197-E206. (PMID: 32407255)
Radiology. 2020 Jun;295(3):715-721. (PMID: 32053470)
Ann Transl Med. 2016 May;4(9):174. (PMID: 27275487)
تواريخ الأحداث: Date Created: 20230222 Latest Revision: 20230224
رمز التحديث: 20230224
مُعرف محوري في PubMed: PMC9931278
DOI: 10.1371/journal.pdig.0000057
PMID: 36812559
قاعدة البيانات: MEDLINE
الوصف
تدمد:2767-3170
DOI:10.1371/journal.pdig.0000057