tetano
Editor, Senior Moderator
Nat Commun
. 2020 Jul 15;11(1):3543.
doi: 10.1038/s41467-020-17280-8.
Early triage of critically ill COVID-19 patients using deep learning
Wenhua Liang[SUP] 1 [/SUP], Jianhua Yao[SUP] 2 [/SUP], Ailan Chen[SUP] 1 3 [/SUP], Qingquan Lv[SUP] 3 [/SUP], Mark Zanin[SUP] 4 [/SUP], Jun Liu[SUP] 1 5 [/SUP], SookSan Wong[SUP] 1 [/SUP], Yimin Li[SUP] 6 [/SUP], Jiatao Lu[SUP] 3 [/SUP], Hengrui Liang[SUP] 1 5 [/SUP], Guoqiang Chen[SUP] 7 [/SUP], Haiyan Guo[SUP] 7 [/SUP], Jun Guo[SUP] 8 [/SUP], Rong Zhou[SUP] 1 [/SUP], Limin Ou[SUP] 1 [/SUP], Niyun Zhou[SUP] 2 [/SUP], Hanbo Chen[SUP] 2 [/SUP], Fan Yang[SUP] 2 [/SUP], Xiao Han[SUP] 2 [/SUP], Wenjing Huan[SUP] 9 [/SUP], Weimin Tang[SUP] 9 [/SUP], Weijie Guan[SUP] 1 [/SUP], Zisheng Chen[SUP] 1 10 [/SUP], Yi Zhao[SUP] 1 [/SUP], Ling Sang[SUP] 1 [/SUP], Yuanda Xu[SUP] 6 [/SUP], Wei Wang[SUP] 5 [/SUP], Shiyue Li[SUP] 1 [/SUP], Ligong Lu[SUP] 11 [/SUP], Nuofu Zhang[SUP] 1 [/SUP], Nanshan Zhong[SUP] 12 [/SUP], Junzhou Huang[SUP] 13 [/SUP], Jianxing He[SUP] 14 [/SUP]
Affiliations
Abstract
The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.
. 2020 Jul 15;11(1):3543.
doi: 10.1038/s41467-020-17280-8.
Early triage of critically ill COVID-19 patients using deep learning
Wenhua Liang[SUP] 1 [/SUP], Jianhua Yao[SUP] 2 [/SUP], Ailan Chen[SUP] 1 3 [/SUP], Qingquan Lv[SUP] 3 [/SUP], Mark Zanin[SUP] 4 [/SUP], Jun Liu[SUP] 1 5 [/SUP], SookSan Wong[SUP] 1 [/SUP], Yimin Li[SUP] 6 [/SUP], Jiatao Lu[SUP] 3 [/SUP], Hengrui Liang[SUP] 1 5 [/SUP], Guoqiang Chen[SUP] 7 [/SUP], Haiyan Guo[SUP] 7 [/SUP], Jun Guo[SUP] 8 [/SUP], Rong Zhou[SUP] 1 [/SUP], Limin Ou[SUP] 1 [/SUP], Niyun Zhou[SUP] 2 [/SUP], Hanbo Chen[SUP] 2 [/SUP], Fan Yang[SUP] 2 [/SUP], Xiao Han[SUP] 2 [/SUP], Wenjing Huan[SUP] 9 [/SUP], Weimin Tang[SUP] 9 [/SUP], Weijie Guan[SUP] 1 [/SUP], Zisheng Chen[SUP] 1 10 [/SUP], Yi Zhao[SUP] 1 [/SUP], Ling Sang[SUP] 1 [/SUP], Yuanda Xu[SUP] 6 [/SUP], Wei Wang[SUP] 5 [/SUP], Shiyue Li[SUP] 1 [/SUP], Ligong Lu[SUP] 11 [/SUP], Nuofu Zhang[SUP] 1 [/SUP], Nanshan Zhong[SUP] 12 [/SUP], Junzhou Huang[SUP] 13 [/SUP], Jianxing He[SUP] 14 [/SUP]
Affiliations
- PMID: 32669540
- DOI: 10.1038/s41467-020-17280-8
Abstract
The sudden deterioration of patients with novel coronavirus disease 2019 (COVID-19) into critical illness is of major concern. It is imperative to identify these patients early. We show that a deep learning-based survival model can predict the risk of COVID-19 patients developing critical illness based on clinical characteristics at admission. We develop this model using a cohort of 1590 patients from 575 medical centers, with internal validation performance of concordance index 0.894 We further validate the model on three separate cohorts from Wuhan, Hubei and Guangdong provinces consisting of 1393 patients with concordance indexes of 0.890, 0.852 and 0.967 respectively. This model is used to create an online calculation tool designed for patient triage at admission to identify patients at risk of severe illness, ensuring that patients at greatest risk of severe illness receive appropriate care as early as possible and allow for effective allocation of health resources.