A Rare Case of Plasmablastic Lymphoma in a Patient with HIV and SARS-CoV-2 Infections.

Lesions commonly associated with HIV infection include oral candidiasis, herpes simplex infection, oral Kaposi's sarcoma, hairy leukoplakia, periodontal diseases (linear gingival erythema and necrotizing ulcerative periodontitis), xerostomia, human papillomavirus-associated warts, aphthous ulcers, non-Hodgkin's lymphoma, histoplasmosis, carcinoma, exfoliative cheilitis, and HIV salivary gland disease. Non-Hodgkin's lymphoma (NHL) is the most common cancer in people living with HIV (PLWH), and the incidence is increased for aggressive B-cell NHL. Plasmablastic lymphoma (PbL) is a rare and aggressive B-cell malignancy that is often unresponsive to chemotherapy and usually has a poor prognosis. We hereby present the case of a patient with a recent history of COVID-19 infection who was diagnosed with HIV and NHL, with manifestations in the oral cavity and a favorable evolution after the introduction of antiviral therapy, specific chemotherapy, and radiotherapy. Dental expertise is necessary for the appropriate management of oral manifestations of HIV infection or AIDS, and lymphoma should be included in the differential diagnosis of any oral lesions.

Bacterial endocarditis masked by COVID-19: A case report.

Infective endocarditis represents a rare complication among patients infected with severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2); it is often a nosocomial infection and the symptomatology can be masked by respiratory failure symptoms from SARS-CoV-2 bronchopneumonia. Management of patients with severe forms of SARS-COV-2 infection who also have associated infective endocarditis is very difficult, especially in mono-specialty hospitals (such as infectious diseases hospitals) where access to cardiological investigations is limited. The current study presents the case of a 73-year-old woman with increased cardiovascular risk (high blood pressure, diabetes mellitus and obesity), with uninvestigated ischaemic heart disease, who was admitted to the Department of Infectious Diseases in the Clinical Infectious Diseases Hospital (Constanta, Romania) due to SARS-CoV-2. Although the evolution was initially favorable, the condition of the patient significantly deteriorated on the 14th day of hospitalization due to the development of Enterococcus faecium infective endocarditis. Despite the therapy, the evolution was fulminant. Infection with coronavirus disease 2019 can result in numerous comorbidities, which cause higher mortality rates than in the general population.

Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science.

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erdos-Rényi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.