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

Autor: Weber GM; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Hong C; Department of Biomedical Informatics, Harvard Medical School, Boston, USA.; Department of Biostatistics and Bioinformatics, Duke University, Durham, USA., Xia Z; Department of Neurology, University of Pittsburgh, Pittsburgh, USA., Palmer NP; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Avillach P; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., L'Yi S; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Keller MS; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Murphy SN; Department of Neurology, Massachusetts General Hospital, Boston, USA., Gutiérrez-Sacristán A; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Bonzel CL; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Serret-Larmande A; Department of biomedical informatics, Hôpital Européen Georges Pompidou, Assistance Publique - Hôpitaux de Paris, Paris, France., Neuraz A; Department of biomedical informatics, Hôpital Necker-Enfants Malade, Assistance Publique Hôpitaux de Paris (APHP), University of Paris, Paris, France., Omenn GS; Department of Computational Medicine & Bioinformatics, Internal Medicine, Human Genetics, and School of Public Health, University of Michigan, Ann Arbor, USA., Visweswaran S; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, USA., Klann JG; Department of Medicine, Massachusetts General Hospital, Boston, USA., South AM; Department of Pediatrics-Section of Nephrology, Brenner Children's Hospital, Wake Forest School of Medicine, Winston Salem, USA., Loh NHW; Department of Anaesthesia, National University Health System, Singapore, Singapore, Singapore., Cannataro M; Department of Medical and Surgical Sciences, Data Analytics Research Center, University Magna Graecia of Catanzaro, Italy, Catanzaro, Italy., Beaulieu-Jones BK; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Bellazzi R; Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Italy, Pavia, Italy., Agapito G; Department of Legal, Economic and Social Sciences, University Magna Graecia of Catanzaro, Italy, Catanzaro, Italy., Alessiani M; Department of Surgery, ASST Pavia, Lombardia Region Health System, Pavia, Italy., Aronow BJ; Departments of Biomedical Informatics, Pediatrics, Cincinnati Children's Hospital Medical Center, University of Cincinnati, Cincinnati, USA., Bell DS; Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, USA., Benoit V; IT department, Innovation & Data, APHP Greater Paris University Hospital, Paris, France., Bourgeois FT; Department of Pediatrics, Harvard Medical School, Boston, USA., Chiovato L; Unit of Internal Medicine and Endocrinology, Istituti Clinici Scientifici Maugeri SpA SB IRCCS, Pavia, Italy., Cho K; Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA., Dagliati A; Department of Electrical Computer and Biomedical Engineering, University of Pavia, Italy, Pavia, Italy., DuVall SL; VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, USA., Barrio NG; Health Informatics, Hospital Universitario 12 de Octubre, Madrid, Spain., Hanauer DA; Department of Learning Health Sciences, University of Michigan, Ann Arbor, USA., Ho YL; Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA., Holmes JH; Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA.; Institute for Biomedical Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA., Issitt RW; Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, UK, London, UK., Liu M; Department of Biostatistics, Harvard School of Public Health, Boston, USA., Luo Y; Department of Preventive Medicine, Northwestern University, Chicago, USA., Lynch KE; VA Informatics and Computing Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, USA., Maidlow SE; Michigan Institute for Clinical and Health Research, University of Michigan, Ann Arbor, USA., Malovini A; Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri SpA SB IRCCS, Pavia, Italy., Mandl KD; Computational Health Informatics Program, Boston Children's Hospital, Boston, USA., Mao C; Department of Preventive Medicine, Northwestern University, Chicago, USA., Matheny ME; VA Informatics and Computing Infrastructure, Tennessee Valley Healthcare System Veterans Affairs Medical Center, Nashville, USA., Moore JH; Institute for Biomedical Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA., Morris JS; Department of Biostatistics, Epidemiology, and Biostatistics, University of Pennysylvania Perelman School of Medicine, Philadelphia, USA., Morris M; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, USA., Mowery DL; Department of Biostatistics, Epidemiology, and Informatics, University of Pennsylvania Perelman School of Medicine, Philadelphia, USA., Ngiam KY; Department of Biomedical informatics, WiSDM, National University Health Systems Singapore, Singapore, Singapore., Patel LP; Department of Internal Medicine, Division of Medical Informatics, University of Kansas Medical Center, Kansas City, USA., Pedrera-Jimenez M; Health Informatics, Hospital Universitario 12 de Octubre, Madrid, Spain., Ramoni RB; Office of Research and Development, Department of Veterans Affairs, Washington, DC, USA., Schriver ER; Data Analytics Center, University of Pennsylvania Health System, Philadelphia, USA., Schubert P; Massachusetts Veterans Epidemiology Research and Information Center (MAVERIC), VA Boston Healthcare System, Boston, USA., Balazote PS; Health Informatics, Hospital Universitario 12 de Octubre, Madrid, Spain., Spiridou A; Digital Research, Informatics and Virtual Environments (DRIVE), Great Ormond Street Hospital for Children, UK, London, UK., Tan ALM; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Tan BWL; Department of Medicine, National University Hospital, Singapore, Singapore, Singapore., Tibollo V; Laboratory of Informatics and Systems Engineering for Clinical Research, Istituti Clinici Scientifici Maugeri SpA SB IRCCS, Pavia, Italy., Torti C; Department of Medical and Surgical Sciences, Infectious and Tropical Disease Unit, University Magna Graecia of Catanzaro, Italy, Catanzaro, Italy., Trecarichi EM; Department of Medical and Surgical Sciences, Infectious and Tropical Disease Unit, University Magna Graecia of Catanzaro, Italy, Catanzaro, Italy., Wang X; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Kohane IS; Department of Biomedical Informatics, Harvard Medical School, Boston, USA., Cai T; Department of Biomedical Informatics, Harvard Medical School, Boston, USA. tcai@hsph.harvard.edu., Brat GA; Department of Biomedical Informatics, Harvard Medical School, Boston, USA. gabriel_brat@hms.harvard.edu.
Jazyk: angličtina
Zdroj: NPJ digital medicine [NPJ Digit Med] 2022 Jun 13; Vol. 5 (1), pp. 74. Date of Electronic Publication: 2022 Jun 13.
DOI: 10.1038/s41746-022-00601-0
Abstrakt: 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.
(© 2022. The Author(s).)
Databáze: MEDLINE
Externí odkaz: