In this document, we report our proposal for modeling the risk of possible contagiousity in a given area monitored by RGB cameras where people freely move and interact. Our system, called Inter-Homines, evaluates in real-time the contagion risk in a monitored area by analyzing video streams: it is able to locate people in 3D space, calculate interpersonal distances and predict risk levels by building dynamic maps of the monitored area. Inter-Homines works both indoor and outdoor, in public and private crowded areas. The software is applicable to already installed cameras or low-cost cameras on industrial PCs, equipped with an additional embedded edge-AI system for temporary measurements. From the AI-side, we exploit a robust pipeline for real-time people detection and localization in the ground plane by homographic transformation based on state-of-the-art computer vision algorithms; it is a combination of a people detector and a pose estimator. From the risk modeling side, we propose a parametric model for a spatio-temporal dynamic risk estimation, that, validated by epidemiologists, could be useful for safety monitoring the acceptance of social distancing prevention measures by predicting the risk level of the scene.

Background There is a paucity of data about the occurrence and risk factors of herpes simplex virus (HSV) reactivation among patients with severe COVID-19 presenting with acute respiratory distress syndrome (ARDS). Methods We performed a nested case-control study among a cohort of SARS-CoV-2 infected patients with ARDS. Between March and April 2020, all consecutive mechanically ventilated patients ≥18 years old with a positive PCR for SARS-CoV-2 on mucocutaneous samples were included in the study. We collected data on demographics, medical history, laboratory variables, administration of antivirals and other agents, respiratory and organ support procedures, microbiological results, and management of ARDS with prone positioning and the use of steroids. Univariate and multivariable Cox regression models were performed in order to identify predictors of HSV reactivation. Results Eighty-three patients with laboratory-confirmed SARS-CoV-2 infection were admitted to the ICU for mechanical ventilation. 18/83 (21.7%) patients developed mucocutaneous herpes simplex virus reactivation after a median of 17 days (IQR, 14–20). Prone positioning was the only independent risk factor for HSV reactivation (adj. hazard ratios, 1.60; 95% CI, 1.11–2.30; P = 0.009). All patients with mucocutaneous HSV reactivation were treated with antivirals. The outcome in terms of ventilator-associated pneumonia, catheter-related bloodstream infections, and in-hospital mortality was similar for patients with and without HSV reactivation. Conclusions HSV reactivation is frequent in COVID-19 patients with ARDS, especially if prolonged invasive mechanical ventilation with prone positioning is needed. Prompt testing for HSV and initiation of antiviral therapy should be performed in case of mucocutaneous lesions in this population.

No abstract

Morbid obesity plays an increasingly important role in healthcare. Patients who are severely obese often suffer from a range of medical problems. One problem is obesity-related hypoventilation syndrome with its resulting hypercapnia. We report a case of a 33-year-old female patient who was in an extraordinarily bad medical state, with severe hypercapnia (pCO2 15.1 kPa), sepsis, acute anuric kidney failure and resulting acidosis (pH 6.96). Her body mass index was 84 kg/m2. Her chances of survival were considered very low after failed attempts at noninvasive ventilation. Based on prior research, we refrained from intubation and chose venovenous extracorporeal membrane oxygenation to treat the hypercapnia. In the entire medical literature, we are not aware of a similarly extraordinary case of obesity-related hypoventilation syndrome that could finally be treated successfully. The idea behind this case report is to consider venovenous extracorporeal membrane oxygenation as an alternative to intubation in this patient collective.