Medical student's perception of the COVID-19 pandemic effect on their education and well-being: a cross-sectional survey in the United States.

BACKGROUND: The effects of drastic curricular changes necessitated by the COVID-19 pandemic on medical students' education and wellbeing have remained largely unstudied. Out study aimed to characterize how medical students were affected by the pandemic, specifically how limitations introduced by the pandemic may have affected the quality, delivery, and experience of medical education. METHODS: Three hundred students from 5 U.S. allopathic medical schools were surveyed to determine students' perceptions about their quality of medical education, professional development, and mental health during the COVID-19 pandemic (October 2020-December 2020). RESULTS: A large majority of students report that while lecture-based learning has not been significantly affected by the pandemic, small-group and clinical learning have greatly declined in quality. Students also reported higher levels of depression, anxiety, and uncertainty with regards to their futures as physicians. CONCLUSIONS: The COVID-19 pandemic has greatly affected the medical student education and wellbeing. Although medical schools have implemented measures to continue to train medical students as effectively as they can, further strategies must be devised to ensure the well-being of students in the present and for future national emergencies.

COVID-19 outcomes in hospitalized patients with active cancer: Experiences from a major New York City health care system.

BACKGROUND: The authors sought to study the risk factors associated with severe outcomes in hospitalized coronavirus disease 2019 (COVID-19) patients with cancer. METHODS: The authors queried the New York University Langone Medical Center's records for hospitalized patients who were polymerase chain reaction-positive for severe acute respiratory syndrome coronavirus 2 (SARS CoV-2) and performed chart reviews on patients with cancer diagnoses to identify patients with active cancer and patients with a history of cancer. Descriptive statistics were calculated and multivariable logistic regression was used to determine associations between clinical, demographic, and laboratory characteristics with outcomes, including death and admission to the intensive care unit. RESULTS: A total of 4184 hospitalized SARS CoV-2+ patients, including 233 with active cancer, were identified. Patients with active cancer were more likely to die than those with a history of cancer and those without any cancer history (34.3% vs 27.6% vs 20%, respectively; P < .01). In multivariable regression among all patients, active cancer (odds ratio [OR], 1.89; CI, 1.34-2.67; P < .01), older age (OR, 1.06; CI, 1.05-1.06; P < .01), male sex (OR for female vs male, 0.70; CI, 0.58-0.84; P < .01), diabetes (OR, 1.26; CI, 1.04-1.53; P = .02), morbidly obese body mass index (OR, 1.87; CI, 1.24-2.81; P < .01), and elevated D-dimer (OR, 6.41 for value >2300; CI, 4.75-8.66; P < .01) were associated with increased mortality. Recent cancer-directed medical therapy was not associated with death in multivariable analysis. Among patients with active cancer, those with a hematologic malignancy had the highest mortality rate in comparison with other cancer types (47.83% vs 28.66%; P < .01). CONCLUSIONS: The authors found that patients with an active cancer diagnosis were more likely to die from COVID-19. Those with hematologic malignancies were at the highest risk of death. Patients receiving cancer-directed therapy within 3 months before hospitalization had no overall increased risk of death. LAY SUMMARY: Our investigators found that hospitalized patients with active cancer were more likely to die from coronavirus disease 2019 (COVID-19) than those with a history of cancer and those without any cancer history. Patients with hematologic cancers were the most likely among patients with cancer to die from COVID-19. Patients who received cancer therapy within 3 months before hospitalization did not have an increased risk of death.

Using Machine Learning of Clinical Data to Diagnose COVID-19

The recent pandemic of Coronavirus Disease 2019 (COVID-19) has placed severe stress on healthcare systems worldwide, which is amplified by the critical shortage of COVID-19 tests. In this study, we propose to generate a more accurate diagnosis model of COVID-19 based on patient symptoms and routine test results by applying machine learning to reanalyzing COVID-19 data from 151 published studies. We aimed to investigate correlations between clinical variables, cluster COVID-19 patients into subtypes, and generate a computational classification model for discriminating between COVID -19 patients and influenza patients based on clinical variables alone. We discovered several novel associations between clinical variables, including correlations between being male and having higher levels of serum lymphocytes and neutrophils. We found that COVID-19 patients could be clustered into subtypes based on serum levels of immune cells, gender, and reported symptoms. Finally, we trained an XGBoost model to achieve a sensitivity of 92.5% and a specificity of 97.9% in discriminating COVID-19 patients from influenza patients. We demonstrated that computational methods trained on large clinical datasets could yield ever more accurate COVID-19 diagnostic models to mitigate the impact of lack of testing. We also presented previously unknown COVID-19 clinical variable correlations and clinical subgroups. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement University of California, Office of the President/Tobacco-Related Disease Research Program Emergency COVID-19 Research Seed Funding Grant (R00RG2369) to W.M.O. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: N/A All necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines and uploaded the relevant EQUATOR Network research reporting checklist(s) and other pertinent material as supplementary files, if applicable. Yes The datasets during and/or analysed during the current study available from the corresponding author on reasonable request.

Using machine learning of clinical data to diagnose COVID-19: a systematic review and meta-analysis.

BACKGROUND: The recent Coronavirus Disease 2019 (COVID-19) pandemic has placed severe stress on healthcare systems worldwide, which is amplified by the critical shortage of COVID-19 tests. METHODS: In this study, we propose to generate a more accurate diagnosis model of COVID-19 based on patient symptoms and routine test results by applying machine learning to reanalyzing COVID-19 data from 151 published studies. We aim to investigate correlations between clinical variables, cluster COVID-19 patients into subtypes, and generate a computational classification model for discriminating between COVID-19 patients and influenza patients based on clinical variables alone. RESULTS: We discovered several novel associations between clinical variables, including correlations between being male and having higher levels of serum lymphocytes and neutrophils. We found that COVID-19 patients could be clustered into subtypes based on serum levels of immune cells, gender, and reported symptoms. Finally, we trained an XGBoost model to achieve a sensitivity of 92.5% and a specificity of 97.9% in discriminating COVID-19 patients from influenza patients. CONCLUSIONS: We demonstrated that computational methods trained on large clinical datasets could yield ever more accurate COVID-19 diagnostic models to mitigate the impact of lack of testing. We also presented previously unknown COVID-19 clinical variable correlations and clinical subgroups.