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 1926526 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 174568 adults who tested positive for SARS-CoV-2 (mean [SD] age, 44.4 [18.6] years; 53.2% female) and 1133848 adult controls who tested negative for SARS-CoV-2 (mean [SD] age, 49.5 [19.2] years; 57.1% female). Of the 174568 adults with SARS-CoV-2, 32472 (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.

It is breathtaking to consider how the response to pandemic viral pathogens has been transformed over the past century by greater knowledge of fundamental biology and technological innovations including PCR and next-generation sequencing. In striking contrast to the current severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) pandemic, the pathogen responsible for the 1918 influenza pandemic was not identified until years after the outbreak. The definitive text in 1927 described influenza as “an epidemiologic conception” likely caused by the bacterium Haemophilus influenzae. Six decades later, HIV-1 was discovered within a few years of the first report of AIDS, although it took another decade before HIV-1 RNA detection methods were sensitive enough to correlate viral load during clinical latency with rate of progression to AIDS. Four decades later, the genomic sequence of SARS-CoV-2 was publicly available on the internet within weeks of the unexplained outbreak of fatal pneumonia that is now known as COVID-19. This critical information enabled academic researchers, vaccine manufacturers, diagnostic laboratories, and some governments to spring into action. In the midst of COVID-19 lockdown, despite collapse of reagent supply chains, independent investigators around the world shared expertise and reagents in order to establish desperately needed local screening programs for SARS-CoV-2. A paper by Yang et al. in PNAS describes the analysis of viral load data from one local screening program, the results of which have important implications for efforts to control the spread of SARS-CoV-2 and for understanding the pathogenesis of SARS-CoV-2 infection.

We present a case of a liver transplant recipient with 2 distinct SARS-CoV-2 infections, separated by 111 days without symptoms and 2 negative test results for SARS-CoV-2 infection. The clinical course suggested reinfection, and viral genomic sequencing was used to distinguish whether the later positive samples were due to SARS-CoV-2 relapse or reinfection.