Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19

Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

Pseudogymnoascus destructans: evidence of virulent skin invasion for bats under natural conditions, Europe

While Pseudogymnoascus destructans has been responsible for mass bat mortalities from white-nose syndrome (WNS) in North America, its virulence in Europe has been questioned. To shed the light on the issue of host-pathogen interaction between European bats and P. destructans, we examined seventeen bats emerging from the fungus-positive underground hibernacula in the Czech Republic during early spring 2013. Dual wing-membrane biopsies were taken from Barbastella barbastellus (1), Myotis daubentonii (1), Myotis emarginatus (1), Myotis myotis (11), Myotis nattereri (1) and Plecotus auritus (2) for standard histopathology and transmission electron microscopy. Non-lethal collection of suspected WNS lesions was guided by trans-illumination of the wing membranes with ultraviolet light. All bats selected for the present study were PCR-positive for P. destructans and showed microscopic findings consistent with the histopathological criteria for WNS diagnosis. Ultramicroscopy revealed oedema of the connective tissue and derangement of the fibroblasts and elastic fibres associated with skin invasion by P. destructans. Extensive fungal infection induced a marked inflammatory infiltration by neutrophils at the interface between the damaged part of the wing membrane replaced by the fungus and membrane tissue not yet invaded by the pathogen. There was no sign of keratinolytic activity in the stratum corneum. Here, we show that lesions pathognomonic for WNS are common in European bats and may also include overwhelming full-thickness fungal growth through the wing membrane equal in severity to reports from North America. Inter-continental differences in the outcome of WNS in bats in terms of morbidity/mortality may therefore not be due to differences in the pathogen itself.