Clinical Characterization and Prediction of Clinical Severity of SARS-CoV-2 Infection Among US Adults Using Data From the US National COVID Cohort Collaborative

Abstract

Importance: The National COVID Cohort Collaborative (N3C) is a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative COVID-19 cohort to date. This multicenter data set can support robust evidence-based development of predictive and diagnostic tools and inform clinical care and policy.

Objectives: To evaluate COVID-19 severity and risk factors over time and assess the use of machine learning to predict clinical severity.

Design, setting, and participants: In a retrospective cohort study of 1 926 526 US adults with SARS-CoV-2 infection (polymerase chain reaction >99% or antigen <1%) and adult patients without SARS-CoV-2 infection who served as controls from 34 medical centers nationwide between January 1, 2020, and December 7, 2020, patients were stratified using a World Health Organization COVID-19 severity scale and demographic characteristics. Differences between groups over time were evaluated using multivariable logistic regression. Random forest and XGBoost models were used to predict severe clinical course (death, discharge to hospice, invasive ventilatory support, or extracorporeal membrane oxygenation).

Main outcomes and measures: Patient demographic characteristics and COVID-19 severity using the World Health Organization COVID-19 severity scale and differences between groups over time using multivariable logistic regression.

Results: The cohort included 174 568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1 133 848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized, and 6565 (20.2%) of those had a severe clinical course (invasive ventilatory support, extracorporeal membrane oxygenation, death, or discharge to hospice). Of the hospitalized patients, mortality was 11.6% overall and decreased from 16.4% in March to April 2020 to 8.6% in September to October 2020 (P = .002 for monthly trend). Using 64 inputs available on the first hospital day, this study predicted a severe clinical course using random forest and XGBoost models (area under the receiver operating curve = 0.87 for both) that were stable over time. The factor most strongly associated with clinical severity was pH; this result was consistent across machine learning methods. In a separate multivariable logistic regression model built for inference, age (odds ratio [OR], 1.03 per year; 95% CI, 1.03-1.04), male sex (OR, 1.60; 95% CI, 1.51-1.69), liver disease (OR, 1.20; 95% CI, 1.08-1.34), dementia (OR, 1.26; 95% CI, 1.13-1.41), African American (OR, 1.12; 95% CI, 1.05-1.20) and Asian (OR, 1.33; 95% CI, 1.12-1.57) race, and obesity (OR, 1.36; 95% CI, 1.27-1.46) were independently associated with higher clinical severity.

Conclusions and relevance: This cohort study found that COVID-19 mortality decreased over time during 2020 and that patient demographic characteristics and comorbidities were associated with higher clinical severity. The machine learning models accurately predicted ultimate clinical severity using commonly collected clinical data from the first 24 hours of a hospital admission.

Figure 1.. Geographic Distribution of Overall SARS-CoV-2–Positive Patients in the US National COVID Cohort Collaborative (N3C) Cohort (N = 1 926 526)

Trend lines show the accumulation of each subregion’s sample size of laboratory-confirmed positive cases in 2020. The Southeast, Middle Atlantic, and Midwestern regions are the most heavily represented, but all regions have substantial patient counts.

Figure 2.. Comorbidity Distributions of the SARS-CoV-2–Positive Cohort (N = 174 568)

See eMethods in Supplement 1 for comorbidity definitions. Patients were stratified using the Clinical Progression Scale (CPS) established by the World Health Organization (WHO) for COVID-19 clinical research (Table). Severity assigned by patient-specific encounter maximum severity. No ED indicates outpatient only without emergency department visit; ED, emergency department visit; moderate, hospitalized without invasive ventilatory support or extracorporeal membrane oxygenation (ECMO); severe, hospitalized with invasive ventilatory support or ECMO; mortality/hospice, hospital death or discharge to hospice.

Figure 3.. Clinical Severity, Age, and Antimicrobial and Immunomodulatory Medication Use Over Time

A, Distribution of the maximum severity of patient-specific encounter among hospitalized patients during 2020. Mortality and invasive ventilatory assistance or extracorporeal membrane oxygenation (severe) have decreased steadily (monthly trend P = .002). Strata were assigned using the Clinical Progression Scale (CPS) established by the World Health Organization (WHO) for COVID-19 clinical research (Table). B, Age distribution of hospitalized patients during 2020. Older patients were more prominent in the spring and the fall, with more younger patients in the summer. C, Evolution of antimicrobial (top) and immunomodulatory (bottom) treatment regimens for hospitalized patients (top 3 severity strata [Table]) during 2020.

Figure 4.. Trajectories of Vital Signs and Laboratory Tests During a Hospital Encounter

A, Medians (line) and interquartile ranges (error bars) of each vital sign on each hospital day, stratified by patient maximum severity (Table). B, Medians (line) and interquartile ranges (error bars) of each laboratory test on each hospital day, stratified by the same severity groups. We tested trajectory differences between severity groups using 1-way analysis of variance at day 7. BNP indicates brain-type natriuretic peptide; Spo₂, saturation as measured by pulse oximetry. SI conversion factors: To convert bilirubin to micromoles per liter, multiply by 17.104; BNP to nanograms per liter, multiply by 1; C-reactive protein to milligrams per liter, multiply by 10; creatinine to micromoles per liter, multiply by 88.4; D-dimer to nanomoles per liter, multiply by 5.476; ferritin to micrograms per liter, multiply by 1; lactate to millimoles per liter, multiply by 0.111; and white blood cells to ×10⁹/L, multiply by 0.001.