lancet-header

Preprints with The Lancet is part of SSRN´s First Look, a place where journals identify content of interest prior to publication. Authors have opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet. The usual SSRN checks and a Lancet-specific check for appropriateness and transparency have been applied. Preprints available here are not Lancet publications or necessarily under review with a Lancet journal. These preprints are early stage research papers that have not been peer-reviewed. The findings should not be used for clinical or public health decision making and should not be presented to a lay audience without highlighting that they are preliminary and have not been peer-reviewed. For more information on this collaboration, see the comments published in The Lancet about the trial period, and our decision to make this a permanent offering, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com.

Predicting COVID-19 Malignant Progression with AI Techniques

29 Pages Posted: 31 Mar 2020

See all articles by Xiang Bai

Xiang Bai

Huazhong University of Science and Technology - School of Electronic Information and Communications

Cong Fang

Huazhong University of Science and Technology - School of Electronic Information and Communications

Yu Zhou

Huazhong University of Science and Technology - School of Electronic Information and Communications

Song Bai

Huazhong University of Science and Technology - School of Electronic Information and Communications

Zaiyi Liu

Southern Medical University - Department of Radiology

Liming Xia

Huazhong University of Science and Technology - Department of Radiology

Qianlan Chen

Huazhong University of Science and Technology - Department of Radiology

Yongchao Xu

Huazhong University of Science and Technology - School of Electronic Information and Communications

Tian Xia

Huazhong University of Science and Technology - School of Electronic Information and Communications

Shi Gong

Huazhong University of Science and Technology - School of Electronic Information and Communications

Xudong Xie

Huazhong University of Science and Technology - School of Electronic Information and Communications

Dejia Song

Huazhong University of Science and Technology - School of Electronic Information and Communications

Ronghui Du

Wuhan Institute for Tuberculosis Control - Department of Pulmonary and Critical care Medicine

Chunhua Zhou

Wuhan Institute for Tuberculosis Control - Department of Radiology

Chengyang Chen

Huazhong University of Science and Technology - Department of Radiology

Dianer Nie

Huazhong University of Science and Technology - Department of Radiology

Lixin Qin

Wuhan Institute for Tuberculosis Control - Department of Radiology

Weiwei Chen

Huazhong University of Science and Technology - Department of Radiology

More...

Abstract

Background: The coronavirus disease 2019 (COVID-19) has become a worldwide pandemic since mid-December 2019, which greatly challenge public medical systems. With limited medical resources, it is a natural strategy, while adopted, to access the severity of patients then determine the treatment priority. However, our work observes the fact that the condition of many mild outpatients quickly worsens in a short time, i.e. deteriorate into severe/critical cases. Hence, it has been crucial to early identify those cases and give timely treatment for optimizing treatment strategy and reducing mortality. This study aims to establish an AI model to predict mild patients with potential malignant progression.

Methods: A total of 133 consecutively mild COVID-19 patients at admission who was hospitalized in Wuhan Pulmonary Hospital from January 3 to February 13, 2020, were selected in this retrospective IRB-approved study. All mild patients at admission were categorized into groups with or without malignant progression. The clinical and laboratory data at admission, the first CT, and the follow-up CT at severe/critical stage of the two groups were compared with Chi-square test, Fisher’s exact test, and t test. Both traditional logistic regression and deep learning-based methods were used to build the prediction models. The area under ROC curve (AUC) was used to evaluate the models.

Findings: The deep learning-based method significantly outperformed logistic regression (AUC 0·954 vs. 0·893). The deep learning-based method achieved a prediction AUC of 0·938 by combining the clinical data and the CT data, significantly outperforming its counterpart trained with clinical data only by 0.141. By further considering the temporal information of the CT sequence, our model achieved the best AUC of 0·954.

Interpretation: The proposed model can be effectively used for finding out the mild patients who are easy to deteriorate into severe/critical cases so that such patients get timely treatments while alleviating the limitations of medical resources.

Funding Statement:This work was supported by National Key R&D Program of China (No. 2018YFB1004600), HUST COVID-19 Rapid Response Call (No. 2020kfyXGYJ093, No. 2020kfyXGYJ094), National Key R&D Program of China (No.2017YFC1309100), National Science Fund for Distinguished Young Scholars (No.81925023), National Natural Science Foundation of China (No.61703049, No. 81771912, No. 81401390)

Declaration of Interests: The authors declare no competing interests.

Ethics Approval Statement: The authors stated this was an IRB-approved study.

Keywords: COVID-19; AI model; prediction; mild patients; potential malignant progression

Suggested Citation

Bai, Xiang and Fang, Cong and Zhou, Yu and Bai, Song and Liu, Zaiyi and Xia, Liming and Chen, Qianlan and Xu, Yongchao and Xia, Tian and Gong, Shi and Xie, Xudong and Song, Dejia and Du, Ronghui and Zhou, Chunhua and Chen, Chengyang and Nie, Dianer and Qin, Lixin and Chen, Weiwei, Predicting COVID-19 Malignant Progression with AI Techniques (3/16/2020). Available at SSRN: https://ssrn.com/abstract=3557984 or http://dx.doi.org/10.2139/ssrn.3557984

Xiang Bai

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Cong Fang

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Yu Zhou

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Song Bai

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Zaiyi Liu

Southern Medical University - Department of Radiology ( email )

Liming Xia

Huazhong University of Science and Technology - Department of Radiology ( email )

No.1095 Jiefang Avenue
Wuhan, 430030
China

Qianlan Chen

Huazhong University of Science and Technology - Department of Radiology

No.1095 Jiefang Avenue
Wuhan, 430030
China

Yongchao Xu

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Tian Xia

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Shi Gong

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Xudong Xie

Huazhong University of Science and Technology - School of Electronic Information and Communications ( email )

Wuhan, 430074
China

Dejia Song

Huazhong University of Science and Technology - School of Electronic Information and Communications

Wuhan, 430074
China

Ronghui Du

Wuhan Institute for Tuberculosis Control - Department of Pulmonary and Critical care Medicine

Wuhan, 430030
China

Chunhua Zhou

Wuhan Institute for Tuberculosis Control - Department of Radiology

Wuhan, 430030
China

Chengyang Chen

Huazhong University of Science and Technology - Department of Radiology

No.1095 Jiefang Avenue
Wuhan, 430030
China

Dianer Nie

Huazhong University of Science and Technology - Department of Radiology

No.1095 Jiefang Avenue
Wuhan, 430030
China

Lixin Qin

Wuhan Institute for Tuberculosis Control - Department of Radiology ( email )

Wuhan, 430030
China

Weiwei Chen (Contact Author)

Huazhong University of Science and Technology - Department of Radiology ( email )

No.1095 Jiefang Avenue
Wuhan, 430030
China