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.

Ultrastructural Pathology of Atherosclerosis, Calcific Aortic Valve Disease, and Bioprosthetic Heart Valve Degeneration: Commonalities and Differences.

Atherosclerosis, calcific aortic valve disease (CAVD), and bioprosthetic heart valve degeneration (alternatively termed structural valve deterioration, SVD) represent three diseases affecting distinct components of the circulatory system and their substitutes, yet sharing multiple risk factors and commonly leading to the extraskeletal calcification. Whereas the histopathology of the mentioned disorders is well-described, their ultrastructural pathology is largely obscure due to the lack of appropriate investigation techniques. Employing an original method for sample preparation and the electron microscopy visualisation of calcified cardiovascular tissues, here we revisited the ultrastructural features of lipid retention, macrophage infiltration, intraplaque/intraleaflet haemorrhage, and calcification which are common or unique for the indicated types of cardiovascular disease. Atherosclerotic plaques were notable for the massive accumulation of lipids in the extracellular matrix (ECM), abundant macrophage content, and pronounced neovascularisation associated with blood leakage and calcium deposition. In contrast, CAVD and SVD generally did not require vasculo- or angiogenesis to occur, instead relying on fatigue-induced ECM degradation and the concurrent migration of immune cells. Unlike native tissues, bioprosthetic heart valves contained numerous specialised macrophages and were not capable of the regeneration that underscores ECM integrity as a pivotal factor for SVD prevention. While atherosclerosis, CAVD, and SVD show similar pathogenesis patterns, these disorders demonstrate considerable ultrastructural differences.