https://www.selleckchem.com/products/bms-1166.html The novel coronavirus (CoV) pandemic is a serious threat for patients with cancer, who have an immunocompromised status and are considered at high risk of infections. Data on the novel CoV respiratory disease (coronavirus disease 2019 [COVID-19]) in patients with cancer are still limited. Unlike other common viruses, CoVs have not been shown to cause a more severe disease in immunocompromised subjects. Along with direct viral pathogenicity, in some individuals, CoV infection triggers an uncontrolled aberrant inflammatory response, leading to lung tissue damage. In patients with cancer treated with immunotherapy (e.g. immune checkpoint inhibitors), COVID-19 may therefore represent a serious threat. After a thorough review of the literature on CoV pathogenesis and cancer, we selected several shared features to define which patients can be considered at higher risk of COVID-19. We combined these clinical and laboratory variables, with the aim of developing a score to weight the risk of COVID-19 in patients with cancer.Background Convolutional neural networks (CNNs) have shown a dermatologist-level performance in the classification of skin lesions. We aimed to deliver a head-to-head comparison of a conventional image analyser (CIA), which depends on segmentation and weighting of handcrafted features, to a CNN trained by deep learning. Methods Cross-sectional study using a real-world, prospectively acquired, dermoscopic dataset of 1981 skin lesions to compare the diagnostic performance of a market-approved CNN (Moleanalyzer-Pro™, developed in 2018) to a CIA (Moleanalyzer-3™/Dynamole™; developed in 2004, all FotoFinder Systems Inc, Germany). As a reference standard, we used histopathological diagnoses (n = 785) or, in non-excised benign lesions (n = 1196), expert consensus plus an uneventful follow-up by sequential digital dermoscopy for at least 2 years. Results A total of 281 malignant lesions and 1700 benign lesions fr