当前位置: X-MOL 学术npj Digit. Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality
npj Digital Medicine ( IF 12.4 ) Pub Date : 2022-06-13 , DOI: 10.1038/s41746-022-00601-0
Griffin M Weber 1 , Chuan Hong 1, 2 , Zongqi Xia 3 , Nathan P Palmer 1 , Paul Avillach 1 , Sehi L'Yi 1 , Mark S Keller 1 , Shawn N Murphy 4 , Alba Gutiérrez-Sacristán 1 , Clara-Lea Bonzel 1 , Arnaud Serret-Larmande 5 , Antoine Neuraz 6 , Gilbert S Omenn 7 , Shyam Visweswaran 8 , Jeffrey G Klann 9 , Andrew M South 10 , Ne Hooi Will Loh 11 , Mario Cannataro 12 , Brett K Beaulieu-Jones 1 , Riccardo Bellazzi 13 , Giuseppe Agapito 14 , Mario Alessiani 15 , Bruce J Aronow 16 , Douglas S Bell 17 , Vincent Benoit 18 , Florence T Bourgeois 19 , Luca Chiovato 20 , Kelly Cho 21 , Arianna Dagliati 22 , Scott L DuVall 23 , Noelia García Barrio 24 , David A Hanauer 25 , Yuk-Lam Ho 21 , John H Holmes 26, 27 , Richard W Issitt 28 , Molei Liu 29 , Yuan Luo 30 , Kristine E Lynch 23 , Sarah E Maidlow 31 , Alberto Malovini 32 , Kenneth D Mandl 33 , Chengsheng Mao 30 , Michael E Matheny 34 , Jason H Moore 27 , Jeffrey S Morris 35 , Michele Morris 8 , Danielle L Mowery 26 , Kee Yuan Ngiam 36 , Lav P Patel 37 , Miguel Pedrera-Jimenez 24 , Rachel B Ramoni 38 , Emily R Schriver 39 , Petra Schubert 21 , Pablo Serrano Balazote 24 , Anastasia Spiridou 28 , Amelia L M Tan 1 , Byorn W L Tan 40 , Valentina Tibollo 32 , Carlo Torti 41 , Enrico M Trecarichi 41 , Xuan Wang 1 , , Isaac S Kohane 1 , Tianxi Cai 1 , Gabriel A Brat 1
Affiliation  

Given the growing number of prediction algorithms developed to predict COVID-19 mortality, we evaluated the transportability of a mortality prediction algorithm using a multi-national network of healthcare systems. We predicted COVID-19 mortality using baseline commonly measured laboratory values and standard demographic and clinical covariates across healthcare systems, countries, and continents. Specifically, we trained a Cox regression model with nine measured laboratory test values, standard demographics at admission, and comorbidity burden pre-admission. These models were compared at site, country, and continent level. Of the 39,969 hospitalized patients with COVID-19 (68.6% male), 5717 (14.3%) died. In the Cox model, age, albumin, AST, creatine, CRP, and white blood cell count are most predictive of mortality. The baseline covariates are more predictive of mortality during the early days of COVID-19 hospitalization. Models trained at healthcare systems with larger cohort size largely retain good transportability performance when porting to different sites. The combination of routine laboratory test values at admission along with basic demographic features can predict mortality in patients hospitalized with COVID-19. Importantly, this potentially deployable model differs from prior work by demonstrating not only consistent performance but also reliable transportability across healthcare systems in the US and Europe, highlighting the generalizability of this model and the overall approach.



中文翻译:


4CE 协作实验室值预测 COVID-19 死亡率的国际比较



鉴于为预测 COVID-19 死亡率而开发的预测算法数量不断增加,我们使用跨国医疗保健系统网络评估了死亡率预测算法的可移植性。我们使用基线常用实验室测量值以及跨医疗保健系统、国家和大陆的标准人口统计和临床协变量来预测 COVID-19 死亡率。具体来说,我们使用九个测量的实验室测试值、入院时的标准人口统计数据以及入院前的合并症负担来训练 Cox 回归模型。这些模型在地点、国家和大陆级别进行了比较。在 39,969 名住院的 COVID-19 患者(68.6% 男性)中,有 5717 人(14.3%)死亡。在 Cox 模型中,年龄、白蛋白、AST、肌酸、CRP 和白细胞计数最能预测死亡率。基线协变量更能预测 COVID-19 住院初期的死亡率。在具有较大队列规模的医疗保健系统中训练的模型在移植到不同地点时很大程度上保留了良好的可移植性性能。入院时的常规实验室检测值与基本人口统计特征相结合可以预测住院的 COVID-19 患者的死亡率。重要的是,这种潜在的可部署模型与之前的工作不同,它不仅展示了一致的性能,而且在美国和欧洲的医疗保健系统中具有可靠的可移植性,突出了该模型和整体方法的普遍性。

更新日期:2022-06-13
down
wechat
bug