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

Abstract

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.

Figure 1:. Geographic, Age, Sex, Race, Ethnicity, and Comorbidity Distributions of N3C Cohort.

Figure 1a shows the representation of each U.S. subregion in the overall (N = 1,926,526) cohort. Trend lines show the accumulation of each subregion’s sample size of lab confirmed positive cases over 2020. The Southeast, Mid-Atlantic, and Midwestern regions are the most heavily represented, but all regions have substantial patient counts. Figure 1b shows the age, sex, race, and ethnicity distributions of the overall N3C cohort, stratified by the N3C phenotype groups (publicly available on GitHub^[c]). Racial and ethnic minorities are well-represented. COVID = coronavirus disease. NHPI = Native Hawaiian or Pacific Islander. Figure 1c shows comorbidity distributions for the laboratory-confirmed positive adult cohort (N = 174,568). See Supplemental Methods for comorbidity definitions. We stratified patients using the Clinical Progression Scale (CPS) established by the World Health Organization (WHO) for COVID-19 clinical research, see Table 1. Severity assigned by patient-specific encounter maximum severity. No ED = outpatient only without emergency department visit, ED = emergency department visit, moderate = hospitalized without invasive ventilation or extracorporeal membrane oxygenation (ECMO), severe = hospitalized with invasive ventilation or ECMO, mortality/hospice = hospital mortality or discharge to hospice.

Figure 2.. Clinical Severity, Age, and Antimicrobial and Immunomodulatory Medication Use Over Time

Figure 2a shows the distribution of patient-specific encounter maximum severity among hospitalized patients during 2020. Mortality and invasive ventilation or extracorporeal membrane oxygenation (“Severe”) have decreased steadily, monthly trend p = 0.002. Strata assigned using the Clinical Progression Scale (CPS) established by the World Health Organization (WHO) for COVID-19 clinical research (hospital mortality or discharge to hospice [black], invasive ventilation or extracorporeal membrane oxygenation [red], hospitalized without any of those [yellow], or emergency department visit only [green], see Table 1). The percentage of patients from each month is shown over each severity group bar. Figure 2b shows how the age distribution of hospitalized patients has changed during 2020. The percentage of patients from each month is shown over each age bracket bar. Older patients (darker blue) were more prominent in the spring and the fall, with more younger patients (lighter blue/teal) in the summer. Figure 2c shows the evolution of antimicrobial and immunomodulatory treatment regimens for hospitalized patients (top 3 severity strata, see Table 1) during 2020.

Figure 3.. Trajectories of Vital Signs and Laboratory Tests During a Hospital Encounter

Figure 3a shows the median (line) and interquartile range (bars) of each vital sign on each hospital day, stratified by patient maximum severity (hospital mortality or discharge to hospice [black], invasive ventilation or extracorporeal membrane oxygenation [red], hospitalized without any of those [yellow], or emergency department visit only [green], see Table 1). Figure 3b shows the median (line) and interquartile range (bars) of each laboratory test on each hospital day, stratified by the same severity groups. BNP = brain natriuretic peptide.

Figure 4.. Variable Importance in the Machine Learning Models Predicting Clinical Severity

The 64 machine learning (ML) model input variables are listed by their mean variable importance rank across ML model types. Each column is a ML model type. Logistic regression is shown without penalization and with L1 and L2 penalties. The table cells show a heat map with darkest (blue) representing highest variable importance and lightest (teal) representing lower variable importance. See Methods and Supplemental Methods for details about variable definitions, model construction, and testing. NTproBNP = N-Terminal-prohormone B-type Natriuretic Peptide.