@Article{info:doi/10.2196/42717,
author="Lee, Hyun Woo
and Yang, Hyun Jun
and Kim, Hyungjin
and Kim, Ue-Hwan
and Kim, Dong Hyun
and Yoon, Soon Ho
and Ham, Soo-Youn
and Nam, Bo Da
and Chae, Kum Ju
and Lee, Dabee
and Yoo, Jin Young
and Bak, So Hyeon
and Kim, Jin Young
and Kim, Jin Hwan
and Kim, Ki Beom
and Jung, Jung Im
and Lim, Jae-Kwang
and Lee, Jong Eun
and Chung, Myung Jin
and Lee, Young Kyung
and Kim, Young Seon
and Lee, Sang Min
and Kwon, Woocheol
and Park, Chang Min
and Kim, Yun-Hyeon
and Jeong, Yeon Joo
and Jin, Kwang Nam
and Goo, Jin Mo",
title="Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study",
journal="J Med Internet Res",
year="2023",
month="Feb",
day="16",
volume="25",
pages="e42717",
keywords="COVID-19; deep learning; artificial intelligence; radiography, thoracic; prognosis; AI model; prediction model; clinical outcome; medical imaging; machine learning",
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. ",
issn="1438-8871",
doi="10.2196/42717",
url="https://www.jmir.org/2023/1/e42717",
url="https://doi.org/10.2196/42717",
url="http://www.ncbi.nlm.nih.gov/pubmed/36795468"
}