Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19.
Comparing machine learning algorithms for predicting ICU admission and mortality in COVID-19.
复制标题
比较机器学习算法用于预测COVID-19的ICU入院和死亡率。
DOI：
10.1038/s41746-021-00456-x
复制
发表时间：
2021-05-21
影响因子：
15.2
通讯作者：
Jain RK
中科院分区：
文献类型：
--
作者：
Subudhi S;Verma A;Patel AB;Hardin CC;Khandekar MJ;Lee H;McEvoy D;Stylianopoulos T;Munn LL;Dutta S;Jain RK
由于预测COVID-19的发展轨迹具有挑战性，机器学习模型可以帮助医生识别高风险个体。这项研究比较了18种机器学习算法在预测COVID-19患者ICU入院和死亡率方面的性能。使用来自马萨诸塞州总布里格姆（MGB）医疗保健数据库的COVID-19患者数据，我们使用2020年3月至4月期间到急诊科（艾德）就诊的患者（n = 3597）开发并内部验证了模型，并使用2020年5月至8月期间到艾德就诊的时间上不同的个体（n = 1711）进一步验证了模型。我们发现，基于集成的模型在预测COVID-19的5天ICU入院和28天死亡率方面优于其他模型类型。CRP、LDH和O2饱和度对于ICU入院模型是重要的，而eGFR <60 ml/min/1.73 m2以及中性粒细胞和淋巴细胞百分比是预测死亡率的最重要变量。实施这些模型可以帮助临床决策未来的传染病爆发，包括COVID-19。
As predicting the trajectory of COVID-19 is challenging, machine learning models could assist physicians in identifying high-risk individuals. This study compares the performance of 18 machine learning algorithms for predicting ICU admission and mortality among COVID-19 patients. Using COVID-19 patient data from the Mass General Brigham (MGB) Healthcare database, we developed and internally validated models using patients presenting to the Emergency Department (ED) between March-April 2020 (n = 3597) and further validated them using temporally distinct individuals who presented to the ED between May-August 2020 (n = 1711). We show that ensemble-based models perform better than other model types at predicting both 5-day ICU admission and 28-day mortality from COVID-19. CRP, LDH, and O2 saturation were important for ICU admission models whereas eGFR <60 ml/min/1.73 m2, and neutrophil and lymphocyte percentages were the most important variables for predicting mortality. Implementing such models could help in clinical decision-making for future infectious disease outbreaks including COVID-19.
登录
查看更多内容
DOI：
10.1053/j.ajkd.2020.09.003
发表时间：
2021-03
期刊：
American journal of kidney diseases : the official journal of the National Kidney Foundation
影响因子：
--
作者：
Flythe JE;Assimon MM;Tugman MJ;Chang EH;Gupta S;Shah J;Sosa MA;Renaghan AD;Melamed ML;Wilson FP;Neyra JA;Rashidi A;Boyle SM;Anand S;Christov M;Thomas LF;Edmonston D;Leaf DE;STOP-COVID Investigators
通讯作者：
STOP-COVID Investigators
影响因子：
3.6
作者：
Liu S;Zhang L;Weng H;Yang F;Jin H;Fan F;Zheng X;Yang H;Li H;Zhang Y;Li J
通讯作者：
Li J
影响因子：
64.8
作者：
Harris CR;Millman KJ;van der Walt SJ;Gommers R;Virtanen P;Cournapeau D;Wieser E;Taylor J;Berg S;Smith NJ;Kern R;Picus M;Hoyer S;van Kerkwijk MH;Brett M;Haldane A;Del Río JF;Wiebe M;Peterson P;Gérard-Marchant P;Sheppard K;Reddy T;Weckesser W;Abbasi H;Gohlke C;Oliphant TE
通讯作者：
Oliphant TE
影响因子：
39.2
作者：
Antommaria, Armand H. Matheny;Gibb, Tyler S.;Eberl, Jason T.
通讯作者：
Eberl, Jason T.
影响因子：
17.1
作者：
Henry, Katharine E.;Hager, David N.;Saria, Suchi
通讯作者：
Saria, Suchi