The value of longitudinal clinical data and paired CT scans in predicting the deterioration of COVID-19 revealed by an artificial intelligence system

Xiaoyang Han; Ziqi Yu; Yaoyao Zhuo; Botao Zhao; Yan Ren; Lorenz Lamm; Xiangyang Xue; Jianfeng Feng; Carsten Marr; Fei Shan; Tingying Peng; Xiao-Yong Zhang

doi:10.1016/j.isci.2022.104227

The value of longitudinal clinical data and paired CT scans in predicting the deterioration of COVID-19 revealed by an artificial intelligence system

iScience. 2022 May 20;25(5):104227. doi: 10.1016/j.isci.2022.104227. Epub 2022 Apr 8.

Authors

Xiaoyang Han^{1

2}, Ziqi Yu^{1

2}, Yaoyao Zhuo^{3

4}, Botao Zhao^{1

2}, Yan Ren⁵, Lorenz Lamm^{6

7}, Xiangyang Xue⁸, Jianfeng Feng^{1

2}, Carsten Marr⁶, Fei Shan⁴, Tingying Peng⁷, Xiao-Yong Zhang^{1

2

9}

Affiliations

¹ Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai 200433, China.
² Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, Ministry of Education, Shanghai 200433, China.
³ Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai 200032, China.
⁴ Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai 201508, China.
⁵ Department of Radiology, Huashan Hospital, Fudan University, Shanghai 200433, China.
⁶ Institute of AI for Health, Helmholtz Zentrum München, Ingolstädter Landstraße 1, D-85764 Neuherberg, Germany.
⁷ Helmholtz AI, Helmholtz Zentrum München, Ingolstädter Landstraße 1, D-85764 Neuherberg, Germany.
⁸ Shanghai Key Laboratory of Intelligent Information Processing, School of Computer Science, Fudan University, Shanghai 200433, China.
⁹ MOE Frontiers Center for Brain Science, Fudan University, Shanghai 200433, China.

Abstract

The respective value of clinical data and CT examinations in predicting COVID-19 progression is unclear, because the CT scans and clinical data previously used are not synchronized in time. To address this issue, we collected 119 COVID-19 patients with 341 longitudinal CT scans and paired clinical data, and we developed an AI system for the prediction of COVID-19 deterioration. By combining features extracted from CT and clinical data with our system, we can predict whether a patient will develop severe symptoms during hospitalization. Complementary to clinical data, CT examinations show significant add-on values for the prediction of COVID-19 progression in the early stage of COVID-19, especially in the 6^th to 8^th day after the symptom onset, indicating that this is the ideal time window for the introduction of CT examinations. We release our AI system to provide clinicians with additional assistance to optimize CT usage in the clinical workflow.

Keywords: artificial intelligence; health sciences; machine learning; microbiology.