Early triage of critically ill COVID-19 patients using deep learning
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 Zhou, Hanbo Chen, Fan Yang, Xiao Han, Wenjing Huan, Weimin Tang, Weijie Guan, Zisheng Chen, Yi Zhao, Ling Sang, Yuanda Xu, Wei Wang, Shiyue Li, Ligong Lu, Nuofu Zhang, Nanshan Zhong, Junzhou Huang, Jianxing He, 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 Zhou, Hanbo Chen, Fan Yang, Xiao Han, Wenjing Huan, Weimin Tang, Weijie Guan, Zisheng Chen, Yi Zhao, Ling Sang, Yuanda Xu, Wei Wang, Shiyue Li, Ligong Lu, Nuofu Zhang, Nanshan Zhong, Junzhou Huang, Jianxing He
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.
Conflict of interest statement
The authors declare no competing interests.
Figures
References
- Guan W-J, et al. Clinical characteristics of coronavirus disease 2019 in China. N. Engl. J. Med. 2020;382:1708–1720. doi: 10.1056/NEJMoa2002032.
- Wu, Z. et al. Characteristics of and important lessons from the coronavirus disease 2019 (COVID-19) outbreak in China: Summary of a report of 72314 cases from the Chinese center for disease control and prevention. JAMA. 10.1001/jama.2020.2648 (2020).
- Cox DR. Regression models and life tables. J. R. Statis. Soc. B. 1972;34:187–220.
- LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436–444. doi: 10.1038/nature14539.
- Esteva A, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–118. doi: 10.1038/nature21056.
- Campanella G, et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images. Nat. Med. 2019;25:1301–1309. doi: 10.1038/s41591-019-0508-1.
- Katzman, J. et al. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med. Res. Methodol. 18, (2018).
- Tibshirani R. Regression shrinkage and selection via the lasso. J. R. Statis. Soc. B. 1996;58:267–288.
- Neill AM, et al. Community acquired pneumonia: aetiology and usefulness of severity criteria on admission. Thorax. 1996;51:179–184. doi: 10.1136/thx.51.10.1010.
- Iasonos A, Schrag D, Raj GV, Panageas KS. How to build and interpret a nomogram for cancer prognosis. J. Clin. Oncol. 2008;26:1364–1370. doi: 10.1200/JCO.2007.12.9791.
- Guan WJ, et al. Comorbidity and its impact on 1,590 patients with COVID-19 in China: a nationwide analysis. Eur. Respiratory J. 2020;55:2000547. doi: 10.1183/13993003.00547-2020.
- Liang W, et al. Cancer patients in SARS-CoV-2 infection: a nationwide analysis in China. Lancet Oncol. 2020;S1470-2045:30096–30096.
- Booth CM, et al. Clinical features and short-term outcomes of 144 patients with SARS in the greater Toronto area. JAMA. 2003;289:2801–2809. doi: 10.1001/jama.289.21.JOC30885.
- Zhou P, et al. A pneumonia outbreak associated with a new coronavirus of probable bat origin. Nature. 2020;579:270–273. doi: 10.1038/s41586-020-2012-7.
- Hamming I, et al. Tissue distribution of ACE2 protein, the functional receptor for SARS coronavirus: a first step in understanding SARS pathogenesis. J. Pathol. 2004;203:631–637. doi: 10.1002/path.1570.
- Buuren S, Groothuis-Oudshoorn K. MICE: multivariate imputation by chained equations in R. J. Stat. Softw. 2011;45:1–67. doi: 10.18637/jss.v045.i03.
- Simon N, Friedman J, Hastie T, Tibshirani R. Regularization paths for Cox’s proportional hazards model via coordinate descent. J. Stat. Softw. 2011;39:1–13. doi: 10.18637/jss.v039.i05.
- Bergstra, J., Yamins, D. & Cox, D. Making a science of model search: hyperparameter optimization in hundreds of dimensions for vision architectures. In Proc. 30th International Conference on Machine Learning 115–123 (2013).
Source: PubMed