RESUMO
Despite available vaccinations COVID-19 case numbers around the world are still growing, and effective medications against severe cases are lacking. In this work, we developed a machine learning model which predicts mortality for COVID-19 patients using data from the multi-center Lean European Open Survey on SARS-CoV-2-infected patients (LEOSS) observational study (>100 active sites in Europe, primarily in Germany), resulting into an AUC of almost 80%. We showed that molecular mechanisms related to dementia, one of the relevant predictors in our model, intersect with those associated to COVID-19. Most notably, among these molecules was tyrosine kinase 2 (TYK2), a protein that has been patented as drug target in Alzheimers Disease but also genetically associated with severe COVID-19 outcomes. We experimentally verified that anti-cancer drugs Sorafenib and Regorafenib showed a clear anti-cytopathic effect in Caco2 and VERO-E6 cells and can thus be regarded as potential treatments against COVID-19. Altogether, our work demonstrates that interpretation of machine learning based risk models can point towards drug targets and new treatment options, which are strongly needed for COVID-19.
RESUMO
ObjectiveHealthcare workers (HCW) are at high risk of SARS-CoV-2 infection due to exposure to potentially infectious material, especially during aerosol-generating procedures (AGP). We aimed to investigate the prevalence of infection among HCW in medical disciplines with AGP. DesignA nationwide questionnaire-based study in in- and outpatient settings was conducted between 12/16/2020 and 01/24/2021. Data on SARS-CoV-2 infections among HCW and potential risk factors were investigated. Results2,070 healthcare facilities with 25,113 employees were included in the study. Despite a higher rate of pre-interventional testing, clinics treated three times more confirmed SARS-CoV-2 cases than private practices (28.8% vs. 88.4%, p<0.001). Overall infection rate among HCW accounted for 4.7%. Multivariate analysis revealed that ZIP-regions having comparably higher incidences were significantly associated with increased risk of infection. Furthermore, clinical setting and the GIE specialty have more than double the risk of infection (OR 2.63; 95% CI 2.501-2.817, p<0.01 and OR 2.35; 95% CI 2.245-2.498, p<0.01). The number of procedures performed per day was also significantly associated with an increased risk of infection (OR 1.01; 95% CI 1.007-1.014), p<0.01). No treatment of confirmed SARS-CoV-2 cases was tending to lower the risk of infection (OR 0.72; 95% CI 0.507-1.025, p=0.068). ConclusionHCW in GIE seem to be at higher risk of infection than those in other AGP, especially in the clinical setting. Regions having comparably higher incidences as well as the number of procedures performed per day were also significantly associated with increased risk of infection. Significance of this studyO_ST_ABSWhat is already known on this subject?C_ST_ABSHealth care workers, especially those exposed to aerosol generating procedures, are assumed to have an increased risk of SARS-CoV-2 infection. However, data confirming this are lacking, especially for the outpatient care setting. What are the new findings?Health care workers in gastrointestinal endoscopy have a higher risk of SARS-CoV-2-infection than in other AGPs. This risk is particularly higher - in clinical settings compared to private practices - in regions having comparably higher incidences - the more procedures are performed per day How might it impact on clinical practice in the foreseeable future?Our study suggests making additional efforts to protect HCW in the gastrointestinal work field.
