Predicting clinical outcomes of SARS-CoV-2 infection during the Omicron wave using machine learning.

The Omicron SARS-CoV-2 variant continues to strain healthcare systems. Developing tools that facilitate the identification of patients at highest risk of adverse outcomes is a priority. The study objectives are to develop population-scale predictive models that: 1) identify predictors of adverse outcomes with Omicron surge SARS-CoV-2 infections, and 2) predict the impact of prioritized vaccination of high-risk groups for said outcome. We prepared a retrospective longitudinal observational study of a national cohort of 172,814 patients in the U.S. Veteran Health Administration who tested positive for SARS-CoV-2 from January 15 to August 15, 2022. We utilized sociodemographic characteristics, comorbidities, and vaccination status, at time of testing positive for SARS-CoV-2 to predict hospitalization, escalation of care (high-flow oxygen, mechanical ventilation, vasopressor use, dialysis, or extracorporeal membrane oxygenation), and death within 30 days. Machine learning models demonstrated that advanced age, high comorbidity burden, lower body mass index, unvaccinated status, and oral anticoagulant use were the important predictors of hospitalization and escalation of care. Similar factors predicted death. However, anticoagulant use did not predict mortality risk. The all-cause death model showed the highest discrimination (Area Under the Curve (AUC) = 0.903, 95% Confidence Interval (CI): 0.895, 0.911) followed by hospitalization (AUC = 0.822, CI: 0.818, 0.826), then escalation of care (AUC = 0.793, CI: 0.784, 0.805). Assuming a vaccine efficacy range of 70.8 to 78.7%, our simulations projected that targeted prevention in the highest risk group may have reduced 30-day hospitalization and death in more than 2 of 5 unvaccinated patients.

Playing Russian roulette with their kids: Experts' construction of ignorance in the California and Ohio measles outbreaks.

Vaccination has become a site of professional and social concern, particularly as parents choose not to vaccinate their children. Previous research in medical sociology has considered the role of parents, knowledge, and health beliefs within vaccination debates. Yet, what has been overlooked is the expert construction of ignorance that emerges in conflicts over vaccination. This construction crystallizes in news media coverage of public health crises created by un- or under-vaccinated populations. Drawing on the sociology of science and the social problems tradition, this article performs a comparative case analysis to reveal that experts' status as privileged knowers affords them the capacity to frame ignorance itself. Using a content analysis of two measles outbreaks-one in California at Disneyland and the second among the Amish in Ohio-I show how experts do not simply traffic in objective, knowledge-based claims. Rather, they incorporate moral valences into these claims, which become apparent through their assessments of ignorance. Experts in the news shape the epistemic contours of the debate, calling out Californians as willfully ignorant, while excusing the Amish as unintentionally ignorant. This framing of ignorance is underpinned by the moral culpability of each population and its tractability to policy intervention. More broadly, this study reveals how expertise can be linked with and even supported by assessments of the causes and motivations of ignorance.