Machine learning based early warning system enables accurate mortality risk prediction for COVID-19

Yue Gao, Guang-Yao Cai, Wei Fang, Hua-Yi Li, Si-Yuan Wang, Lingxi Chen, Yang Yu, Dan Liu, Sen Xu, Peng-Fei Cui, Shao-Qing Zeng, Xin-Xia Feng, Rui-Di Yu, Ya Wang, Yuan Yuan, Xiao-Fei Jiao, Jian-Hua Chi, Jia-Hao Liu, Ru-Yuan Li, Xu Zheng, Chun-Yan Song, Ning Jin, Wen-Jian Gong, Xing-Yu Liu, Lei Huang, Xun Tian, Lin Li, Hui Xing, Ding Ma, Chun-Rui Li, Fei Ye () and Qing-Lei Gao ()
Additional contact information
Yue Gao: Huazhong University of Science and Technology
Guang-Yao Cai: Huazhong University of Science and Technology
Wei Fang: Wuhan University
Hua-Yi Li: Huazhong University of Science and Technology
Si-Yuan Wang: Huazhong University of Science and Technology
Lingxi Chen: City University of Hong Kong Shenzhen Research Institute
Yang Yu: Huazhong University of Science and Technology
Dan Liu: Huazhong University of Science and Technology
Sen Xu: Huazhong University of Science and Technology
Peng-Fei Cui: Huazhong University of Science and Technology
Shao-Qing Zeng: Huazhong University of Science and Technology
Xin-Xia Feng: Huazhong University of Science and Technology
Rui-Di Yu: Huazhong University of Science and Technology
Ya Wang: Huazhong University of Science and Technology
Yuan Yuan: Huazhong University of Science and Technology
Xiao-Fei Jiao: Huazhong University of Science and Technology
Jian-Hua Chi: Huazhong University of Science and Technology
Jia-Hao Liu: Huazhong University of Science and Technology
Ru-Yuan Li: Huazhong University of Science and Technology
Xu Zheng: Huazhong University of Science and Technology
Chun-Yan Song: Huazhong University of Science and Technology
Ning Jin: Huazhong University of Science and Technology
Wen-Jian Gong: Huazhong University of Science and Technology
Xing-Yu Liu: Huazhong University of Science and Technology
Lei Huang: Huazhong University of Science and Technology
Xun Tian: Huazhong University of Science and Technology
Lin Li: Affiliated Hospital of Hubei University of Arts and Science
Hui Xing: Affiliated Hospital of Hubei University of Arts and Science
Ding Ma: Huazhong University of Science and Technology
Chun-Rui Li: Huazhong University of Science and Technology
Fei Ye: Huazhong University of Science and Technology
Qing-Lei Gao: Huazhong University of Science and Technology

Nature Communications, 2020, vol. 11, issue 1, 1-10

Abstract: Abstract Soaring cases of coronavirus disease (COVID-19) are pummeling the global health system. Overwhelmed health facilities have endeavored to mitigate the pandemic, but mortality of COVID-19 continues to increase. Here, we present a mortality risk prediction model for COVID-19 (MRPMC) that uses patients’ clinical data on admission to stratify patients by mortality risk, which enables prediction of physiological deterioration and death up to 20 days in advance. This ensemble model is built using four machine learning methods including Logistic Regression, Support Vector Machine, Gradient Boosted Decision Tree, and Neural Network. We validate MRPMC in an internal validation cohort and two external validation cohorts, where it achieves an AUC of 0.9621 (95% CI: 0.9464–0.9778), 0.9760 (0.9613–0.9906), and 0.9246 (0.8763–0.9729), respectively. This model enables expeditious and accurate mortality risk stratification of patients with COVID-19, and potentially facilitates more responsive health systems that are conducive to high risk COVID-19 patients.

Date: 2020
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.nature.com/articles/s41467-020-18684-2 Abstract (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:natcom:v:11:y:2020:i:1:d:10.1038_s41467-020-18684-2

Ordering information: This journal article can be ordered from
https://www.nature.com/ncomms/

DOI: 10.1038/s41467-020-18684-2

Access Statistics for this article

Nature Communications is currently edited by Nathalie Le Bot, Enda Bergin and Fiona Gillespie

More articles in Nature Communications from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().