IMPORTANCEThe National COVID Cohort Collaborative (N3C) is a centralized, harmonized, highgranularity 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 PARTICIPANTSIn 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 MEASURESPatient 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. RESULTSThe 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, (continued) Key Points Question In a US data resource large enough to adjust for multiple confounders, what risk factors are associated with COVID-19 severity and severity trajectory over time, and can machine learning models predict clinical severity? Findings In this cohort study of 174 568 adults with SARS-CoV-2, 32 472 (18.6%) were hospitalized and 6565 (20.2%) were severely ill, and first-day machine learning models accurately predicted clinical severity. Mortality was 11.6%

The shape of the legislative agenda varies through the legislative process. At the policy debate stage, where legislative proposals are introduced, packaged, and debated, members' bill cosponsoring patterns reveal a multidimensional agenda. At the decision stage on the legislative floor, members' voting patterns reveal a low-dimensional agenda. This article compares the dimensional structures of legislators' bill cosponsoring and floor voting activities during the 103rd and 104th Congresses. The analyses show that bill cosponsoring contains at least three and as many as five distinct dimensions, suggesting that pre-floor legislative activities play an important role in structuring the lines of conflict for floor decisions.

Only one study of patient satisfaction with eVisit acute primary care services was identified, and this suggests that previous analyses of eVisit utilization are lacking this key component of healthcare service delivery evaluations. The delivery of primary care via eVisits on mobile platforms is still in adolescence, with few methodologically rigorous analyses of outcomes of efficiency, patient health, and satisfaction.

BACKGROUND Few studies have assessed adherence to non-vitamin K antagonist oral anticoagulants (NOACs), especially using contemporary data now that multiple NOACs are available. OBJECTIVE To compare adherence and treatment patterns among NOACs for stroke prevention in patients with nonvalvular atrial fibrillation (NVAF). METHODS Incident and treatment-naive NVAF patients were identified during 2013–2014 from a large claims database in this retrospective cohort study. Patients were included who initiated rivaroxaban, dabigatran, or apixaban within 30 days after diagnosis. Adherence to the index medication and adherence to any oral anticoagulant was assessed using the proportion of days covered (PDC) at 3, 6, and 9 months. The number of switches and gaps in therapy were also evaluated. Analyses were stratified by stroke risk scores, and a logistic regression model was used to control for factors that may predict high adherence. RESULTS Dabigatran had lower adherence (PDC = 0.76, 0.64, 0.57) compared with rivaroxaban (PDC = 0.83, 0.73, 0.66; P < 0.001) and apixaban (PDC = 0.82, 0.72, 0.66; P < 0.001) at 3, 6, and 9 months of follow-up and twice the number of switches to either other anticoagulants or antiplatelet therapy. Adherence was higher overall as stroke risk increased, and dabigatran had consistently lower adherence compared with the other NOACs. Multivariable logistic regression predicting PDC ≥ 0.80 showed rivaroxaban users with higher odds of high adherence compared with dabigatran or rivaroxaban across all time periods. Adjusted analyses showed that increasing age and comorbid hypertension and diabetes were associated with higher adherence. CONCLUSIONS In this real-world analysis of adherence to NOACs, rivaroxaban and apixaban had favorable unadjusted adherence profiles compared with dabigatran, while rivaroxaban users had higher odds of high adherence (PDC ≥ 0.80) among the NOACs in adjusted analyses. Clinicians and managed care organizations should consider the implications of lower adherence on clinical outcomes and quality assessment.