logo
ResearchBunny Logo
Abstract
This study demonstrates a deep learning-based survival model that predicts the risk of COVID-19 patients developing critical illness using clinical characteristics at admission. The model, trained on a cohort of 1590 patients and validated on three independent cohorts (totaling 1393 patients), achieved high concordance indexes (0.894, 0.890, 0.852, and 0.967). An online tool based on this model facilitates patient triage at admission, enabling early identification of high-risk patients and efficient allocation of healthcare resources.
Publisher
NATURE COMMUNICATIONS
Published On
Jul 15, 2020
Authors
Wenhua Liang, Jianhua Yao, Ailan Chen, Qingquan Lv, Mark Zanin, Jun Liu, SookSan Wong, Yimin Li, Jiatao Lu, Hengrui Liang, Guoqiang Chen, Haiyan Guo, Jun Guo, Rong Zhou, Limin Ou, Niyun Zhuo, Hanbo Chen, Fan Yang, Xiao Han, Wenjing Huang, Weimin Tang, Weijie Guan, Zisheng Chen, Yi Zhao, Ling Sang, Yuanda Xu, Wei Wang, Shiyue Li, Ligong Lu, Nuofu Zhang, Nanshan Zhong, Junzhuo Huang, Jianxing He
Tags
COVID-19
deep learning
critical illness
survival model
patient triage
healthcare resources
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs—just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny