Search

Objectives: Men have a higher mortality rate and more severe COVID-19 infection than women. The mechanism for this is unclear. We hypothesise that innate sex differences, rather than comorbidity burden, drive higher male mortality., Design: Retrospective cohort., Setting: Montefiore Health System (MHS) in Bronx, New York, USA., Participants: A cohort population of 364 992 patients at MHS between 1 January 2018 and 1 January 2020 was defined, from which individuals hospitalised during the pre-COVID period (1 January 2020-15 February 2020) (n=5856) and individuals hospitalised during the COVID-19 surge (1 March 2020-15 April 2020) (n=4793) were examined for outcomes. A subcohort with confirmed COVID-19+ hospitalisation was also examined (n=1742)., Primary and Secondary Outcome Measures: Hospitalisation and in-hospital mortality., Results: Men were older, had more comorbidities, lower body mass index and were more likely to smoke. Unadjusted logistic regression showed a higher odds of death in hospitalised men than women during both the pre-COVID-19 and COVID-19 periods (pre-COVID-19, OR: 1.66 vs COVID-19 OR: 1.98). After adjustment for relevant clinical and demographic factors, the higher risk of male death attenuated towards the null in the pre-COVID-19 period (OR 1.36, 95% CI 1.05 to 1.76) but remained significantly higher in the COVID-19 period (OR 2.02; 95% CI 1.73 to 2.34).In the subcohort of COVID-19+ hospitalised patients, men had 1.37 higher odds of in-hospital death (95% CI 1.09 to 1.72), which was not altered by adjustment for comorbidity (OR remained at 1.38 (95% CI 1.08 to 1.76)) but was attenuated with addition of initial pulse oximetry on presentation (OR 1.26, 95% CI 0.99 to 1.62)., Conclusions: Higher male mortality risk during the COVID-19 period despite adjustment for comorbidity supports the role of innate physiological susceptibility to COVID-19 death. Attenuation of higher male risk towards the null after adjustment for severity of lung disease in hospitalised COVID-19+ patients further supports the role of higher severity of COVID-19 pneumonia in men., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2022. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Context: Recommendations for COVID-safe, in-person, high school education have included masks and distancing between students but do not describe a scalable surveillance solution to rapidly identify and mitigate disease prevalence or exposure., Methods: Through an Internet application, all school participants reported symptoms, illness, or exposure daily. Physician-supervised follow-up interviews were reviewed and recorded in daily rounds. Students and faculty were allowed or prohibited to enter school based on the results., Results: From August 30, 2020, until April 13, 2021, a high school in Bergen County, New Jersey (an epicenter of high COVID prevalence), with 889 students and 214 faculty members, staff, and volunteers, generated 1497 assessments. Reasons for initial evaluation included 48 (3%) participants with positive COVID tests, 520 (34%) COVID-exposed, 178 (12%) exposed to someone with symptoms and unknown COVID status, 208 (14%) subjects with symptoms themselves, 525 (35%) exposed to a high-risk geography or air travel, and 12 (1%) contacts of a contact. Of the 61 subjects ultimately diagnosed with COVID, the sources of infection were 36 (57%) home exposure, 16 (27%) confirmed nonschool sources, 8 (13%) unknown, 1 (2%) travel to a high-risk area, and only one potential case of in-school transmission., Conclusions: Masks, distance, and aggressive contact tracing supported by an Internet application with consistent application of quarantine protocols successfully permitted in-school education without COVID spread in a high prevalence environment. This finding remains important to guide safety measures should vaccine-resistant strains-or new pandemics-challenge us in the future., Competing Interests: The authors have no conflicts of interest relevant to this article to disclose., (Copyright © 2022 Wolters Kluwer Health, Inc. All rights reserved.)

Background: During a pandemic, it is important for clinicians to stratify patients and decide who receives limited medical resources. Machine learning models have been proposed to accurately predict COVID-19 disease severity. Previous studies have typically tested only one machine learning algorithm and limited performance evaluation to area under the curve analysis. To obtain the best results possible, it may be important to test different machine learning algorithms to find the best prediction model., Objective: In this study, we aimed to use automated machine learning (autoML) to train various machine learning algorithms. We selected the model that best predicted patients' chances of surviving a SARS-CoV-2 infection. In addition, we identified which variables (ie, vital signs, biomarkers, comorbidities, etc) were the most influential in generating an accurate model., Methods: Data were retrospectively collected from all patients who tested positive for COVID-19 at our institution between March 1 and July 3, 2020. We collected 48 variables from each patient within 36 hours before or after the index time (ie, real-time polymerase chain reaction positivity). Patients were followed for 30 days or until death. Patients' data were used to build 20 machine learning models with various algorithms via autoML. The performance of machine learning models was measured by analyzing the area under the precision-recall curve (AUPCR). Subsequently, we established model interpretability via Shapley additive explanation and partial dependence plots to identify and rank variables that drove model predictions. Afterward, we conducted dimensionality reduction to extract the 10 most influential variables. AutoML models were retrained by only using these 10 variables, and the output models were evaluated against the model that used 48 variables., Results: Data from 4313 patients were used to develop the models. The best model that was generated by using autoML and 48 variables was the stacked ensemble model (AUPRC=0.807). The two best independent models were the gradient boost machine and extreme gradient boost models, which had an AUPRC of 0.803 and 0.793, respectively. The deep learning model (AUPRC=0.73) was substantially inferior to the other models. The 10 most influential variables for generating high-performing models were systolic and diastolic blood pressure, age, pulse oximetry level, blood urea nitrogen level, lactate dehydrogenase level, D-dimer level, troponin level, respiratory rate, and Charlson comorbidity score. After the autoML models were retrained with these 10 variables, the stacked ensemble model still had the best performance (AUPRC=0.791)., Conclusions: We used autoML to develop high-performing models that predicted the survival of patients with COVID-19. In addition, we identified important variables that correlated with mortality. This is proof of concept that autoML is an efficient, effective, and informative method for generating machine learning-based clinical decision support tools., (©Kenji Ikemura, Eran Bellin, Yukako Yagi, Henny Billett, Mahmoud Saada, Katelyn Simone, Lindsay Stahl, James Szymanski, D Y Goldstein, Morayma Reyes Gil. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 26.02.2021.)