The COVID-19 outbreak has spread extensively around the world. Loss of smell and taste have emerged as main predictors for COVID-19. The objective of our study is to develop a comprehensive machine learning (ML) modelling framework to assess the predictive value of smell and taste disorders, along with other symptoms, in COVID-19 infection. A multicenter case-control study was performed, in which suspected cases for COVID-19, who were tested by real-time reverse-transcription polymerase chain reaction (RT-PCR), informed about the presence and severity of their symptoms using visual analog scales (VAS). ML algorithms were applied to the collected data to predict a COVID-19 diagnosis using a 50-fold cross-validation scheme by randomly splitting the patients in training (75%) and testing datasets (25%). A total of 777 patients were included. Loss of smell and taste were found to be the symptoms with higher odds ratios of 6.21 and 2.42 for COVID-19 positivity. The ML algorithms applied reached an average accuracy of 80%, a sensitivity of 82%, and a specificity of 78% when using VAS to predict a COVID-19 diagnosis. This study concludes that smell and taste disorders are accurate predictors, with ML algorithms constituting helpful tools for COVID-19 diagnostic prediction.

Biliary tract infections are frequent, and a significant cause of morbidity and mortality. Bacteremia is common in these infections, particularly in the elderly and patients with cancer.

To study the association between detection of the Clostridioides difficile gene encoding the binary toxin (CDT) and direct detection of toxinB (TcdB) from feces with the appearance of serious disease, complications, or recurrence in a prospective series of cases. A total of 220 confirmed cases were included, using a two-step algorithm: an initial study to detect the enzyme, glutamate dehydrogenase (GDH), followed, in cases of positivity, by detection of the tcdB. tcdB-positive patients were investigated for the presence of CDT and TcdB. Outcome variables were severe disease, the modified Illinois C. difficile infection (CDI) prognostic risk index (ZAR score), the appearance of complications (need for colectomy, CDI-related death, or toxic megacolon) and recurrence. Patients who tested positive for the presence of TcdB in feces were found to have greater disease severity than those who tested negative, with a ZAR score of 35.4% vs. 23% (p = .048), a higher recurrence rate (14.6% vs. 5.9%, p = .032), and a tendency for higher number of complications (20.7% vs. 11.5%), although without reaching statistical significance (p = .053). When presence of CDT was analyzed, higher frequencies of severe disease (39.2% vs. 21.2%, p = .005), complications and recurrence (21.6% vs. 10.9%, p = .037 and 14.9% vs. 5.8%, p = .029; respectively) were observed in patients where CDT was detected. TcdB and CDT act as prognostic markers of the appearance of serious disease, complications or recurrence in cases of CDI. Simultaneous detection of both markers, TcdB and CDT, had a greater impact on the prognosis than when they were detected separately.

Background. The aim of this study was to investigate the incidence of COVID-19-associated pulmonary aspergillosis (CAPA) in critically ill patients and the impact of anticipatory antifungal treatment on the incidence of CAPA in critically ill patients. Methods. Before/after observational study in a mixed intensive care unit (ICU) of a university teaching hospital. The study took place between March 2020 and June 2022. Inclusion criteria were critically ill patients with severe SARS-CoV-2 pneumonia requiring invasive mechanical ventilation. Two analysis periods were compared according to whether or not antifungal therapy was given early. Results. A total of 160 patients with severe SARS-CoV-2 pneumonia and invasive mechanical ventilation were included. The incidence of CAPA in the first study period was 19 out of 58 patients (32.75%); during the second period, after implementation of the intervention (anticipatory antifungal therapy), the incidence of CAPA decreased to 10.78% (11 out of 102 patients). In patients with CAPA under invasive mechanical ventilation, the mortality rate decreased from 100% to 64%. Conclusions. Anticipating antifungal treatment in patients with SARS-CoV-2 pneumonia under invasive mechanical ventilation was associated with a decrease in the incidence and mortality of pulmonary aspergillosis.