Objective: Tick-borne encephalitis (TBE) is an endemic zoonotic viral disease in many European countries and in the central and eastern parts of Asia. Slovakia reports the highest occurrence of alimentary tick-borne encephalitis in Europe, after the consumption of unpasteurized milk and cheese from domestic ruminants. In May 2016, an outbreak of tick-borne encephalitis that emerged after the consumption of sheep cheese occurred in eastern Slovakia. In total, 44 people were ill and 36 were hospitalized. Methods: Data from the 36 hospitalized patients at the Department of Infectology and Travel Medicine in Košice with TBE were retrospectively analysed from the medical documentation. The patients were contacted 3 years after discharge. Results: Twenty of the hospitalized patients had meningoencephalitis and 16 had meningitis. The main symptoms that occurred in all patients were fever and headache. Nuchal rigidity was seen in 50% of the patients. Three patients developed late systemic complications and another six patients had psychiatric complications. None of the patients died. Three years after the disease onset, 52% of contacted patients reported persistent discomfort. Conclusions: TBE is an infection with a wide range of clinical courses. Our findings suggest that alimentary-acquired TBE lead to severe disease and persistent discomfort.

Deep neural network models have produced significant results in solving various challenging tasks, including medical diagnostics. To increase the credibility of these black-box models in the eyes of doctors, it is necessary to focus on their explainability. Several papers have been published combining deep learning methods with selected types of explainability methods, usually aimed at analyzing medical image data, including ECG images. The ECG is specific because its image representation is only a secondary visualization of stream data from sensors. However, explainability methods for stream data are rarely investigated. Therefore, in this article we focus on the explainability of black-box models for stream data from 12-lead ECG. We designed and implemented a perturbation explainability method and verified it in a user study on a group of medical students with experience in ECG tagging in their final years of study. The results demonstrate the suitability of the proposed method, as well as the importance of including multiple data sources in the diagnostic process.

This study assessed age-specific measles immunity in healthcare professionals who were at risk of occupational infection during the 2018 measles epidemic in Slovakia. The goal was to identify measles-susceptible age groups and to compare findings with the 2018 National Immunological Survey. Data from 546 healthcare professionals at the Children's Faculty Hospital in Košice, Slovakia, were collected from September to December 2018. Based on epidemiological history, the cohort of healthcare professionals was categorized into measles-immune and measles-susceptible groups. Samples from measles-susceptible healthcare professionals were analyzed for measles IgG antibodies. Of the 546 healthcare professionals at risk of occupational infection, 294 (53.8 %) were classified as measles-susceptible. Seropositivity was detected in 252 (85.7 %) healthcare professionals; 33 (11.2 %) were seronegative, and nine (3.1 %) yielded equivocal results. The lowest age-specific immunity rates within the measles-susceptible cohort were found in the 30–34 years (61.5 %) and 35–39 years (69.1 %) age groups. This corresponds to the lowest seropositivity (68.3 %) observed in the 35–39 age group in the 2018 National Immunological Survey. The low measles immunity observed in specific adult cohorts highlights the need for routine serological screening and targeted re-vaccination of susceptible individuals, particularly among healthcare professionals in high-risk hospital settings.

Objective—To identify effective data analytics and machine learning solutions that can help in the decision-making process in the medical domain and contribute to the understanding of COVID-19 disease. In this study, we analyze data from anonymized electronic medical records of 4711 patients with COVID-19 disease admitted to hospital in Atlanta. Methods—We used random forest, LightGBM, XGBoost, CatBoost, KNN, SVM, logistic regression, and MLP neural network models in this work. The models are evaluated depending on the type of prediction by relevant metrics, especially accuracy, F1-score, and ROC AUC score. Another aim of the work was to find out which factors most affected severity and mortality risk among the patients. To identify the important features, different statistical methods were used, as well as LASSO regression, and explainable artificial intelligence (XAI) method SHAP values for model explainability. The best models were implemented in a web application and tested by medical experts. The model for prediction of mortality risk was tested on a validation cohort of 45 patients from the Department of Infectiology and Travel Medicine, L. Pasteur University Hospital in Košice (UNLP). Results—Our study shows that the best model for predicting COVID-19 disease severity was the LightGBM model with accuracy of 88.4% using all features and 89.5% using the eight most important features. The best model for predicting mortality risk was also the LightGBM model, which achieved a ROC AUC score of 83.7% and a classification accuracy of 81.2% using all features. Using a simplified model trained on the 15 most important features, the ROC AUC score was 83.6% and the classification accuracy was 80.5%. We deployed the simplified models for predicting COVID-19 disease severity and for predicting the risk of COVID-19-related death in a web-based application and tested them with medical experts. This test resulted in a ROC AUC score of 83.6% and an overall prediction accuracy of 73.3%.

Cytomegalovirus (CMV) is a ubiquitous herpesvirus infecting a large proportion of the population worldwide. Clinical manifestations range from asymptomatic infection to severe disease with multi-organ involvement, depending primarily on host immune status. CMV hepatitis is an uncommon clinical presentation. In pregnancy, infection is usually asymptomatic in immunocompetent women; however, transplacental transmission may occur, leading to congenital infection. Congenital CMV is the most common congenital viral infection. This report describes the case of a 30-year-old pregnant woman with acute CMV infection acquired during the first trimester. The disease manifested as hepatitis, with ALT and AST levels reaching up to 31-fold and 15-fold above the upper limits of normal, respectively. Gradual improvement was observed with supportive treatment, and the outcome was favourable for both mother and child. The infant was delivered at term and has shown normal development; at 8 years of age, the only reported condition is lactose intolerance.