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

Yue Gao,Lingxi Chen,Ya Wang,Wei Fang,Guangyao Cai ,Wenjian Gong ,Xun Tian,Jiahao Liu ,Lei Huang,Hui Xing,Ding Ma,Xu Zheng,Shaoqing Zeng ,Sen Xu,Ning Jin,Fei Ye,Huayi Li ,Dan Liu,Yang Yu,Xingyu Liu ,Rui Yu ,Xiang Feng ,Pengfei Cui ,Xue Jiao ,Chunrui Li ,Yuan Yuan,Jianhua Chi ,Ruyuan Li ,Siyuan Wang ,Lin Li,Chunyan Song ,Qinglei Gao

doi:10.1038/s41467-020-18684-2

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.

Highlights

Soaring cases of coronavirus disease (COVID-19) are pummeling the global health system
The validated capability of enabling expeditious and accurate mortality risk stratification of COVID-19 may facilitate more responsive health systems that are conducive to high-risk COVID-19 patients via early identification, and ensuing instant intervention as well as intensive care and monitoring, hopefully assisting to save lives during the pandemic
Nonsurvivors had significantly (p < 0.001) advanced age, higher levels of BUN and D-dimer, and lower levels of SpO2, lymphocyte, ALB, and PLT (Fig. 4c and Supplementary Table 5). These findings were parallel to risk factors of mortality of COVID19 delineated previously[16], indicating that the selected features were highly relevant to prognosis. In this multicenter retrospective study, we built the mortality risk prediction model for COVID-19 (MRPMC), an ensemble model derived from four Machine learning (ML) algorithms (LR, support vector machine (SVM), gradient boosted decision tree (GBDT), and neural network (NN)), that enabled accurate prediction of physiological deterioration and death for COVID-19 patients up to 20 days in advance using clinical information in Electronic health records (EHRs) on admission, and validated it both internally and externally

Summary

Introduction

Soaring cases of coronavirus disease (COVID-19) are pummeling the global health system. 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. 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. The validated capability of enabling expeditious and accurate mortality risk stratification of COVID-19 may facilitate more responsive health systems that are conducive to high-risk COVID-19 patients via early identification, and ensuing instant intervention as well as intensive care and monitoring, hopefully assisting to save lives during the pandemic

Objectives

Methods

Results

Conclusion