Cardiovascular and Renal Comorbidities Included into Neural Networks Predict the Outcome in COVID-19 Patients Admitted to an Intensive Care Unit: Three-Center, Cross-Validation, Age- and Sex-Matched Study.

Here, we performed a multicenter, age- and sex-matched study to compare the efficiency of various machine learning algorithms in the prediction of COVID-19 fatal outcomes and to develop sensitive, specific, and robust artificial intelligence tools for the prompt triage of patients with severe COVID-19 in the intensive care unit setting. In a challenge against other established machine learning algorithms (decision trees, random forests, extra trees, neural networks, k-nearest neighbors, and gradient boosting: XGBoost, LightGBM, and CatBoost) and multivariate logistic regression as a reference, neural networks demonstrated the highest sensitivity, sufficient specificity, and excellent robustness. Further, neural networks based on coronary artery disease/chronic heart failure, stage 3-5 chronic kidney disease, blood urea nitrogen, and C-reactive protein as the predictors exceeded 90% sensitivity and 80% specificity, reaching AUROC of 0.866 at primary cross-validation and 0.849 at secondary cross-validation on virtual samples generated by the bootstrapping procedure. These results underscore the impact of cardiovascular and renal comorbidities in the context of thrombotic complications characteristic of severe COVID-19. As aforementioned predictors can be obtained from the case histories or are inexpensive to be measured at admission to the intensive care unit, we suggest this predictor composition is useful for the triage of critically ill COVID-19 patients.

Ventilation-Associated Particulate Matter Is a Potential Reservoir of Multidrug-Resistant Organisms in Health Facilities.

Most healthcare-associated infections (HCAIs) develop due to the colonisation of patients and healthcare workers by multidrug-resistant organisms (MDRO). Here, we investigated whether the particulate matter from the ventilation systems (Vent-PM) of health facilities can harbour MDRO and other microbes, thereby acting as a potential reservoir of HCAIs. Dust samples collected in the ventilation grilles and adjacent air ducts underwent a detailed analysis of physicochemical properties and biodiversity. All Vent-PM samples included ultrafine PM capable of reaching the alveoli. Strikingly, >70% of Vent-PM samples were contaminated, mostly by viruses (>15%) or multidrug-resistant and biofilm-producing bacterial strains (60% and 48% of all bacteria-contaminated specimens, respectively). Total viable count at 1 m from the ventilation grilles was significantly increased after opening doors and windows, indicating an association between air flow and bacterial contamination. Both chemical and microbial compositions of Vent-PM considerably differed across surgical vs. non-surgical and intensive vs. elective care units and between health facilities located in coal and chemical districts. Reduced diversity among MDRO and increased prevalence ratio in multidrug-resistant to the total Enterococcus spp. in Vent-PM testified to the evolving antibiotic resistance. In conclusion, we suggest Vent-PM as a previously underestimated reservoir of HCAI-causing pathogens in the hospital environment.