The National COVID Cohort Collaborative: Clinical Characterization and Early Severity Prediction.

Autor:	Bennett TD; Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA., Moffitt RA; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Hajagos JG; Stony Brook University, Stony Brook, NY, USA., Amor B; Palantir Technologies, Denver, CO, USA., Anand A; Stony Brook University, Stony Brook, NY, USA., Bissell MM; Palantir Technologies, Denver, CO, USA., Bradwell KR; Palantir Technologies, Denver, CO, USA., Bremer C; Stony Brook University, Stony Brook, NY, USA., Byrd JB; The University of Michigan at Ann Arbor, Ann Arbor, MI, USA., Denham A; University of Rochester Medical Center, Rochester, NY, USA., DeWitt PE; Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA., Gabriel D; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Garibaldi BT; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Girvin AT; Palantir Technologies, Denver, CO, USA., Guinney J; Sage Bionetworks, Seattle, WA, USA., Hill EL; University of Rochester Medical Center, Rochester, NY, USA., Hong SS; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Jimenez H; Stony Brook University, Stony Brook, NY, USA., Kavuluru R; University of Kentucky, Lexington, KY, USA., Kostka K; Real World Solutions, IQVIA, Cambridge, MA, USA.; Observational Health Data Sciences and Informatics, New York, NY, USA., Lehmann HP; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Levitt E; University of Alabama at Birmingham, Birmingham, AL, USA., Mallipattu SK; Stony Brook University, Stony Brook, NY, USA., Manna A; Palantir Technologies, Denver, CO, USA., McMurry JA; Translational and Integrative Sciences Center, Oregon State University, Corvallis, OR, USA., Morris M; Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA, USA., Muschelli J; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Neumann AJ; Translational and Integrative Sciences Center, Oregon State University, Corvallis, OR, USA., Palchuk MB; TriNetX, Cambridge, MA, USA., Pfaff ER; North Carolina Translational and Clinical Sciences Institute (NC TraCS), University of North Carolina at Chapel Hill, Chapel Hill, NC, USA., Qian Z; Stony Brook University, Stony Brook, NY, USA., Qureshi N; Palantir Technologies, Denver, CO, USA., Russell S; Section of Informatics and Data Science, Department of Pediatrics, University of Colorado School of Medicine, University of Colorado, Aurora, CO, USA., Spratt H; University of Texas Medical Branch, Galveston, TX, USA., Walden A; Sage Bionetworks, Seattle, WA, USA.; Oregon Clinical and Translational Research Institute, Oregon Health & Science University, Portland, OR, USA., Williams AE; Tufts Medical Center Clinical and Translational Science Institute, Tufts Medical Center, Boston, MA, USA., Wooldridge JT; Stony Brook University, Stony Brook, NY, USA., Yoo YJ; Stony Brook University, Stony Brook, NY, USA., Zhang XT; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Zhu RL; Johns Hopkins University School of Medicine, Baltimore, MD, USA., Austin CP; National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, MD, USA., Saltz JH; Department of Biomedical Informatics, Stony Brook University, Stony Brook, NY, USA., Gersing KR; National Center for Advancing Translational Sciences, National Institutes of Health, Bethesda, MD, USA., Haendel MA; Oregon Clinical and Translational Research Institute, Oregon Health & Science University, Portland, OR, USA.; Translational and Integrative Sciences Center, Dept. of Molecular Toxicology, Oregon State University, Corvallis, OR, USA., Chute CG; Schools of Medicine, Public Health, and Nursing, Johns Hopkins University, Baltimore, MD, USA.
Jazyk:	angličtina
Zdroj:	MedRxiv : the preprint server for health sciences [medRxiv] 2021 Jan 23. Date of Electronic Publication: 2021 Jan 23.
DOI:	10.1101/2021.01.12.21249511
Abstrakt:	Background: The majority of U.S. reports of COVID-19 clinical characteristics, disease course, and treatments are from single health systems or focused on one domain. Here we report the creation of the National COVID Cohort Collaborative (N3C), a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative U.S. cohort of COVID-19 cases and controls to date. This multi-center dataset supports robust evidence-based development of predictive and diagnostic tools and informs critical care and policy. Methods and Findings: In a retrospective cohort study of 1,926,526 patients from 34 medical centers nationwide, we stratified patients using a World Health Organization COVID-19 severity scale and demographics; we then evaluated differences between groups over time using multivariable logistic regression. We established vital signs and laboratory values among COVID-19 patients with different severities, providing the foundation for predictive analytics. The cohort included 174,568 adults with severe acute respiratory syndrome associated with SARS-CoV-2 (PCR >99% or antigen <1%) as well as 1,133,848 adult patients that served as lab-negative controls. Among 32,472 hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March/April 2020 to 8.6% in September/October 2020 (p = 0.002 monthly trend). In a multivariable logistic regression model, age, male sex, liver disease, dementia, African-American and Asian race, and obesity were independently associated with higher clinical severity. To demonstrate the utility of the N3C cohort for analytics, we used machine learning (ML) to predict clinical severity and risk factors over time. Using 64 inputs available on the first hospital day, we predicted a severe clinical course (death, discharge to hospice, invasive ventilation, or extracorporeal membrane oxygenation) using random forest and XGBoost models (AUROC 0.86 and 0.87 respectively) that were stable over time. The most powerful predictors in these models are patient age and widely available vital sign and laboratory values. The established expected trajectories for many vital signs and laboratory values among patients with different clinical severities validates observations from smaller studies, and provides comprehensive insight into COVID-19 characterization in U.S. patients. Conclusions: This is the first description of an ongoing longitudinal observational study of patients seen in diverse clinical settings and geographical regions and is the largest COVID-19 cohort in the United States. Such data are the foundation for ML models that can be the basis for generalizable clinical decision support tools. The N3C Data Enclave is unique in providing transparent, reproducible, easily shared, versioned, and fully auditable data and analytic provenance for national-scale patient-level EHR data. The N3C is built for intensive ML analyses by academic, industry, and citizen scientists internationally. Many observational correlations can inform trial designs and care guidelines for this new disease. Competing Interests: Declaration of interests Benjamin Amor, Katie Rebecca Bradwell, Andrew T. Girvin, Amin Manna, and Nabeel Qureshi: employee of Palantir Technologies; Brian T. Garibaldi: Member of the FDA Pulmonary-Allergy Drugs Advisory Committee (PADAC); Matvey B. Palchuk: employee of TriNetX; Kristin Kostka: employee of IQVIA Inc.; Julie A. McMurry: and Melissa A. Haendel Cofounders of Pryzm Health; Chris P. Austin and Ken R. Gersing, employees of the National Institutes of Health. No conflicts of interest reported for all other authors.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu