Weber Griffin M, Hong Chuan, Xia Zongqi, Palmer Nathan P, Avillach Paul, L'Yi Sehi, Keller Mark S, Murphy Shawn N, Gutiérrez-Sacristán Alba, Bonzel Clara-Lea, Serret-Larmande Arnaud, Neuraz Antoine, Omenn Gilbert S, Visweswaran Shyam, Klann Jeffrey G, South Andrew M, Loh Ne Hooi Will, Cannataro Mario, Beaulieu-Jones Brett K, Bellazzi Riccardo, Agapito Giuseppe, Alessiani Mario, Aronow Bruce J, Bell Douglas S, Benoit Vincent, Bourgeois Florence T, Chiovato Luca, Cho Kelly, Dagliati Arianna, DuVall Scott L, Barrio Noelia García, Hanauer David A, Ho Yuk-Lam, Holmes John H, Issitt Richard W, Liu Molei, Luo Yuan, Lynch Kristine E, Maidlow Sarah E, Malovini Alberto, Mandl Kenneth D, Mao Chengsheng, Matheny Michael E, Moore Jason H, Morris Jeffrey S, Morris Michele, Mowery Danielle L, Ngiam Kee Yuan, Patel Lav P, Pedrera-Jimenez Miguel, Ramoni Rachel B, Schriver Emily R, Schubert Petra, Balazote Pablo Serrano, Spiridou Anastasia, Tan Amelia L M, Tan Byorn W L, Tibollo Valentina, Torti Carlo, Trecarichi Enrico M, Wang Xuan, Kohane Isaac S, Cai Tianxi, Brat Gabriel A
Department of Biomedical Informatics, Harvard Medical School, Boston, USA.
Department of Biostatistics and Bioinformatics, Duke University, Durham, USA.
NPJ Digit Med. 2022 Jun 13;5(1):74. doi: 10.1038/s41746-022-00601-0.
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.
鉴于为预测新冠肺炎死亡率而开发的预测算法数量不断增加，我们利用一个跨国医疗系统网络评估了一种死亡率预测算法的可转移性。我们使用医疗系统、国家和各大洲中常见的基线实验室测量值以及标准人口统计学和临床协变量来预测新冠肺炎死亡率。具体而言，我们用九个测量的实验室检测值、入院时的标准人口统计学数据以及入院前的合并症负担训练了一个Cox回归模型。这些模型在机构、国家和大洲层面进行了比较。在39969例新冠肺炎住院患者中（男性占68.6%），5717例（14.3%）死亡。在Cox模型中，年龄、白蛋白、谷草转氨酶、肌酸、C反应蛋白和白细胞计数对死亡率的预测作用最大。基线协变量在新冠肺炎住院早期对死亡率的预测性更强。在队列规模较大的医疗系统中训练的模型在移植到不同机构时，很大程度上保留了良好的可转移性表现。入院时的常规实验室检测值与基本人口统计学特征相结合，可以预测新冠肺炎住院患者的死亡率。重要的是，这个潜在可部署的模型与之前的研究不同，它不仅表现出一致的性能，而且在美国和欧洲的医疗系统中都具有可靠的可转移性，突出了该模型及整体方法的普遍性。
