International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality

Weber GM, Hong C, Xia Z, Palmer NP, Avillach P, L'Yi S, Keller MS, Murphy SN, Gutierrez-Sacristan A, Bonzel CL, Serret-Larmande A, Neuraz A, Omenn GS, Visweswaran S, Klann JG, South AM, Loh NHW, Cannataro M, Beaulieu-Jones BK, Bellazzi R, Agapito G, Alessiani M, Aronow BJ, Bell DS, Benoit V, Bourgeois FT, Chiovato L, Cho K, Dagliati A, Duvall SL, Barrio NG, Hanauer DA, Ho YL, Holmes JH, Issitt RW, Liu M, Luo Y, Lynch KE, Maidlow SE, Malovini A, Mandl KD, Mao C, Matheny ME, Moore JH, Morris JS, Morris M, Mowery DL, Ngiam KY, Patel LP, Pedrera-Jimenez M, Ramoni RB, Schriver ER, Schubert P, Balazote PS, Spiridou A, Tan ALM, Tan BWL, Tibollo V, Torti C, Trecarichi EM, Wang X, Kohane IS, Cai T, Brat GA (2022)

Publication Type: Journal article

Publication year: 2022

Journal

Book Volume: 5

Article Number: 74

Journal Issue: 1

DOI: 10.1038/s41746-022-00601-0

Abstract

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.

Additional Organisation(s)

Involved external institutions

Harvard University United States (USA) (US) National University Health System (NUHS) Singapore (SG) University of Pittsburgh United States (USA) (US) George E. Wahlen Department of Veterans Affairs Medical Center United States (USA) (US) University of Paris 4 - Paris-Sorbonne / Université paris IV Paris-Sorbonne France (FR) Istituti Clinici Scientifici (ICS) Maugeri Spa Italy (IT) University of Cincinnati United States (USA) (US) Magna Græcia University of Catanzaro / Università degli studi Magna Græcia di Catanzaro Italy (IT) Hospital Universitario 12 de Octubre Spain (ES) Massachusetts General Hospital United States (USA) (US) University of Kansas Medical Center United States (USA) (US) Veterans Affairs Healthcare System Boston and Harvard Medical School United States (USA) (US) University of Pennsylvania United States (USA) (US) University of Michigan United States (USA) (US) Tennessee Valley Healthcare System United States (USA) (US) Wake Forest University United States (USA) (US) Assistance Publique-Hôpitaux de Paris (AP-HP) France (FR) Northwestern University United States (USA) (US) Great Ormond Street Hospital (GOSH) United Kingdom (GB) Veterans Health Administration (VHA) United States (USA) (US) Università degli Studi di Pavia Italy (IT) Boston Children's Hospital United States (USA) (US) University of Pennsylvania Health System (UPHS, Penn Medicine) United States (USA) (US) Azienda Socio-Sanitaria Territoriale di Pavia / ASST Pavia Italy (IT) University of California Los Angeles (UCLA) United States (USA) (US) Georges Pompidou European Hospital / Hôpital Européen Georges-Pompidou (HEGP) France (FR)

How to cite

APA:

Weber, G.M., Hong, C., Xia, Z., Palmer, N.P., Avillach, P., L'Yi, S.,... Brat, G.A. (2022). International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality. npj Digital Medicine, 5(1). https://dx.doi.org/10.1038/s41746-022-00601-0

MLA:

Weber, Griffin M., et al. "International comparisons of laboratory values from the 4CE collaborative to predict COVID-19 mortality." npj Digital Medicine 5.1 (2022).

BibTeX: Download