Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study

• DOI: 10.2196/42717
• Publication Date: 2023-02-16T16:01:26Z
• Authors: Hyun Woo Lee; Hyun Jun Yang; Hyungjin Kim; Ue-Hwan Kim; Dong Hyun Kim; Soon Ho Yoon; Soo-Youn Ham; Bo Da Nam; Kum Ju Chae; Dabee Lee; Jin Young Yoo; So Hyeon Bak; Jin Young Kim; Jin Hwan Kim; Ki Beom Kim; Jung Im Jung; Jae-Kwang Lim; Jong Eun Lee; Myung Jin Chung; Young Kyung Lee; Young Seon Kim; Sang Min Lee; Woocheol Kwon; Chang Min Park; Yun-Hyeon Kim; Yeon Joo Jeong; Kwang Nam Jin; Jin Mo Goo
• Keywords: Chest radiograph

An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19.We aimed to develop and validate a prediction CXR based on an AI clinical variables predict outcomes patients with COVID-19.This retrospective longitudinal study included hospitalized COVID-19 at multiple medical centers between February 2020 October 2020. Patients Boramae Medical Center were randomly classified into training, validation, internal testing sets (at ratio of 8:1:1, respectively). initial images as input, logistic regression information, combined the output (as score) information developed trained hospital length stay (LOS) ≤2 weeks, need oxygen supplementation, acute respiratory distress syndrome (ARDS). The models externally validated Korean Imaging Cohort data set discrimination calibration.The suboptimal LOS weeks or supplementation but performed acceptably ARDS (AI area under curve [AUC] 0.782, 95% CI 0.720-0.845; AUC 0.878, 0.838-0.919). better predicting (AUC 0.704, 0.646-0.762) 0.890, 0.853-0.928) compared score alone. Both showed calibration (P=.079 P=.859).The model, comprising was having acceptable severe illness excellent COVID-19.