Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study
Authors:
- Hyun Woo LeeHLHyun Woo Lee
- Hyun Jun YangHYHyun Jun Yang
- Hyungjin KimHKHyungjin Kim
- Ue-Hwan KimUKUe-Hwan Kim
- Dong Hyun KimDKDong Hyun Kim
- Soon Ho YoonSYSoon Ho Yoon
- Soo-Youn HamSHSoo-Youn Ham
- Bo Da NamBNBo Da Nam
- Kum Ju ChaeKCKum Ju Chae
- Dabee LeeDLDabee Lee
- Jin Young YooJYJin Young Yoo
- So Hyeon BakSBSo Hyeon Bak
Open Access
- 16 February 2023
- journal article
- research article
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 25 (1) , e42717
Abstract
Background: An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19. Objective: We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19. Methods: This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration. Results: The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859). Conclusions: The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.Keywords
All Related Versions
This publication has 33 references indexed in Scilit:
- Severe Covid-19New England Journal of Medicine, 2020
- Early intervention likely improves mortality in COVID-19 infectionClinical Medicine, 2020
- Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisalBMJ, 2020
- Lower mortality of COVID-19 by early recognition and intervention: experience from Jiangsu ProvinceAnnals of Intensive Care, 2020
- The role of CT for Covid-19 patient’s management remains poorly definedAnnals of Translational Medicine, 2020
- Development and Validation of a Multivariable Lung Cancer Risk Prediction Model That Includes Low-Dose Computed Tomography Screening ResultsJAMA Network Open, 2019
- Beyond discrimination: A comparison of calibration methods and clinical usefulness of predictive models of readmission riskJournal of Biomedical Informatics, 2017
- Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statementBMJ, 2014
- Receiver Operating Characteristic Curve in Diagnostic Test AssessmentJournal of Thoracic Oncology, 2010
- Comparing the Areas under Two or More Correlated Receiver Operating Characteristic Curves: A Nonparametric ApproachBiometrics, 1988