lancet-header
Preprints with The Lancet is part of SSRN´s First Look, a place where journals and other research experts identify content of interest prior to publication. These preprint papers are not peer-reviewed. Authors have either opted in at submission to The Lancet family of journals to post their preprints on Preprints with The Lancet, or submitted directly via SSRN. 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 papers should not be used for clinical decision making or reporting of research to a lay audience without indicating that this is preliminary research that has not been peer-reviewed. For more information see the Comment published in The Lancet, or visit The Lancet´s FAQ page, and for any feedback please contact preprints@lancet.com

Eleven Routine Clinical Features Predict COVID-19 Severity Uncovered by Machine Learning of Longitudinal Measurements

29 Pages Posted: 17 Sep 2020

See all articles by Kai Zhou

Kai Zhou

Wenzhou Medical University - Affiliated Taizhou Hospital

Yaoting Sun

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Lu Li

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Zelin Zang

Westlake University - School of Engineering

Jing Wang

Wenzhou Medical University - Affiliated Taizhou Hospital

Jun Li

Wenzhou Medical University - Department of Clinical Laboratory

Junbo Liang

Wenzhou Medical University - Affiliated Taizhou Hospital

Fangfei Zhang

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Qiushi Zhang

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

Weigang Ge

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Hao Chen

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Xindong Sun

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

Liang Yue

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

Xiaomai Wu

Wenzhou Medical University - Affiliated Taizhou Hospital

Bo Shen

Wenzhou Medical University - Affiliated Taizhou Hospital

Jiaqin Xu

Wenzhou Medical University - Affiliated Taizhou Hospital

Hongguo Zhu

Taizhou Enze Hospital - Health Clinic for Enze Precision Medicine

Shiyong Chen

Wenzhou Medical University - Department of Clinical Laboratory

Hai Yang

Wenzhou Medical University - Affiliated Taizhou Hospital

Shigao Huang

University of Macau - Cancer Centre

Minfei Peng

Wenzhou Medical University - Affiliated Taizhou Hospital

Dongqing Lv

Wenzhou Medical University - Affiliated Taizhou Hospital

Chao Zhang

Wenzhou Medical University - Affiliated Taizhou Hospital

Haihong Zhao

Wenzhou Medical University - Affiliated Taizhou Hospital

Luxiao Hong

Wenzhou Medical University - Affiliated Taizhou Hospital

Zhehan Zhou

Wenzhou Medical University - Affiliated Taizhou Hospital

Haixiao Chen

Wenzhou Medical University - Affiliated Taizhou Hospital

Xuejun Dong

Zhejiang University - School of Medicine

Chunyu Tu

Zhejiang University - School of Medicine

Ming-Hui Li

Shaoxing People's Hospital - Department of Infectious Diseases

Yi Zhu

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

Baofu Chen

Wenzhou Medical University - Affiliated Taizhou Hospital

Stan Z. Li

Westlake University - School of Engineering

Tiannan Guo

Westlake Institute for Advanced Study - School of Life Sciences; Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

More...

Abstract

Background: Severity prediction of COVID-19 remains one of the major clinical challenges for the ongoing pandemic. In this study, we aim to establish a model for COVID-19 severity prediction and depict dynamic changes of key clinical features over 7 weeks.

Methods: In our retrospective study, a total of 841 patients have been screened with the SARS-CoV-2 nucleic acid test, of which 144 patients were virus RNA (COVID-19) positive, resulting in a data matrix containing of 3,065 readings for 124 types of measurements from 17 categories. We built a support vector machine model assisted with genetic algorithm for feature selection based on the longitudinal measurement. 25 patients as a test cohort were included from an independent hospital.

Findings: A panel of 11 routine clinical factors constructed a classifier for COVID-19 severity prediction, achieving an accuracy of over 94%. Validation of the model in an independent cohort containing 25 patients achieved an accuracy of 80%. The overall sensitivity, specificity, PPV and NPV were 0.70, 0.99, 0.93 and 0.93, respectively. This study presents a practical model for timely severity prediction for COVID-19, which is freely available at a webserver https://guomics.shinyapps.io/covidAI/.

Interpretation: The model provided a classifier composed of 11 routine clinical features which are widely available during COVID-19 management which could predict the severity and may guide the medical care of COVID-19 patients.

Funding: This work is supported by grants from Tencent Foundation (2020), National Natural Science Foundation of China (81972492, 21904107, 81672086), Zhejiang Provincial Natural Science Foundation for Distinguished Young Scholars (LR19C050001), Hangzhou Agriculture and Society Advancement Program (20190101A04).

Declaration of Interests: NA

Ethics Approval Statement: This study was approved by the Medical Ethics Committee of Taizhou Hospital, Shaoxing People’s Hospital and Westlake University, Zhejiang province of China, and informed consent was obtained from each enrolled subject.

Keywords: COVID-19, SARS-CoV-2, Machine learning, Routine clinical test

Suggested Citation

Zhou, Kai and Sun, Yaoting and Li, Lu and Zang, Zelin and Wang, Jing and Li, Jun and Liang, Junbo and Zhang, Fangfei and Zhang, Qiushi and Ge, Weigang and Chen, Hao and Sun, Xindong and Yue, Liang and Wu, Xiaomai and Shen, Bo and Xu, Jiaqin and Zhu, Hongguo and Chen, Shiyong and Yang, Hai and Huang, Shigao and Peng, Minfei and Lv, Dongqing and Zhang, Chao and Zhao, Haihong and Hong, Luxiao and Zhou, Zhehan and Chen, Haixiao and Dong, Xuejun and Tu, Chunyu and Li, Ming-Hui and Zhu, Yi and Chen, Baofu and Li, Stan Z. and Guo, Tiannan, Eleven Routine Clinical Features Predict COVID-19 Severity Uncovered by Machine Learning of Longitudinal Measurements. Available at SSRN: https://ssrn.com/abstract=3669140 or http://dx.doi.org/10.2139/ssrn.3669140

Kai Zhou

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Yaoting Sun

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Lu Li

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Zelin Zang

Westlake University - School of Engineering

China

Jing Wang

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Jun Li

Wenzhou Medical University - Department of Clinical Laboratory ( email )

China

Junbo Liang

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Fangfei Zhang

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Qiushi Zhang

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

China

Weigang Ge

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Hao Chen

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Xindong Sun

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

China

Liang Yue

Westlake University - Key Laboratory of Structural Biology of Zhejiang Province

China

Xiaomai Wu

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Bo Shen

Wenzhou Medical University - Affiliated Taizhou Hospital ( email )

Taizhou
China

Jiaqin Xu

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Hongguo Zhu

Taizhou Enze Hospital - Health Clinic for Enze Precision Medicine ( email )

Taizhou
China

Shiyong Chen

Wenzhou Medical University - Department of Clinical Laboratory ( email )

China

Hai Yang

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Shigao Huang

University of Macau - Cancer Centre ( email )

China

Minfei Peng

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Dongqing Lv

Wenzhou Medical University - Affiliated Taizhou Hospital ( email )

Taizhou
China

Chao Zhang

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Haihong Zhao

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Luxiao Hong

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Zhehan Zhou

Wenzhou Medical University - Affiliated Taizhou Hospital

Taizhou
China

Haixiao Chen

Wenzhou Medical University - Affiliated Taizhou Hospital ( email )

Taizhou
China

Xuejun Dong

Zhejiang University - School of Medicine

866 Yuhangtang Road
Binjiang
Hangzhou, Zhejiang 310058
China

Chunyu Tu

Zhejiang University - School of Medicine

866 Yuhangtang Road
Binjiang
Hangzhou, Zhejiang 310058
China

Ming-Hui Li

Shaoxing People's Hospital - Department of Infectious Diseases ( email )

Shaoxing, Zhejiang 312000
China

Yi Zhu

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences ( email )

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Baofu Chen

Wenzhou Medical University - Affiliated Taizhou Hospital ( email )

Taizhou
China

Stan Z. Li

Westlake University - School of Engineering ( email )

China

Tiannan Guo (Contact Author)

Westlake Institute for Advanced Study - School of Life Sciences ( email )

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Westlake Institute for Advanced Study - Institute of Basic Medical Sciences ( email )

18 Shilongshan Road
Hangzhou, Zhejiang Province 310024
China

Click here to go to TheLancet.com

Paper statistics

Abstract Views
293
Downloads
21
PlumX Metrics