Decentralised Federated Learning for Hospital Networks with application to COVID-19 Detection

Federated Learning (FL) is a distributed machine learning technique which enables local learning of global machine learning models without the need of exchanging data. The original FL algorithm, Federated Averaging (FedAvg), is extended in this work by means of consensus theory. Differently from standard FL algorithms, the resulting one, named FedLCon, does not need a coordinating server, which represents a single failure point and needs to be trusted by all the clients. Furthermore, the consensus paradigm is also applied to the Adaptive Federated Learning (AdaFed) algorithm, which extends FedAvg with an adaptive model averaging procedure. Performance comparison tests are performed over a real-world COVID-19 detection scenario. Author

The Short-Term Psychological Impact of Covid-19: A Systematic Review of the Literature

Covid-19 has originally spread in Wuhan, China, in December 2019. The disease causes respiratory impairments and many other complications, such as fatigue, fever, muscle soreness and, in some cases, diarrhea and nausea, and can lead to death. The correlation between infectious diseases and psychological distress has already emerged during other epidemics, for example during SARS (Severe Acute Respiratory Syndrome) and Ebola. We conducted this systematic review to investigate the short-term psychological consequences of Covid-19 on the general population. Through a thematic analysis procedure, recurring themes have been identified. The most significant results concern the impact of social media, anxiety, and depression. In particular, fake news reported by the media increase the level of anxiety experienced by the population, and factors like being young or being old, being a student, being single or widow, along with a low level of education, further exacerbate anxiety symptoms. On the other hand, following the guidelines proposed by the government and having clear and comprehensible information were identified as protective factors. Our findings highlighted the need to monitor the high-risk population and to investigate the long-term effects of the pandemic.

Recommendations for the suspected diagnosis and management of Multisystemic Inflammatory Syndrome (MIS-C) in the context of a SARS-CoV-2 pandemic. April 2021

Multisystem inflammatory syndrome temporally associated with COVID-19 (MIS-C) is a post-infectious complication described in children and adolescents with previous exposure to SARS-CoV-2. Because of its potential to evolve to severe disease-including cardiovascular impairment and multiple organ failure-it requires a prompt diagnosis and appropriate management, including intensive care for most cases. These guidelines compile recent information from scientific literature, from our local clinical experiences during the past pandemic year, and have been discussed by experts. The recommendations provided are meant to help the clinical work of health teams attending the pediatric population.

Recommendations for the suspected diagnosis and management of multisystemic inflammatory syndrome (Mis-c) in the context of a sars-cov-2 pandemic. april 2021

Multisystem inflammatory syndrome temporally associated with COVID-19 (MIS-C) is a post-infectious complication described in children and adolescents with previous exposure to SARS-CoV-2. Because of its potential to evolve to severe disease-including cardiovascular impairment and multiple organ failure-it requires a prompt diagnosis and appropriate management, including intensive care for most cases. These guidelines compile recent information from scientific literature, from our local clinical experiences during the past pandemic year, and have been discussed by experts. The recommendations provided are meant to help the clinical work of health teams attending the pediatric population.