Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients.

This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of healthcare and 2) to investigate the research question of what does "trustworthy AI" mean at the time of the COVID-19 pandemic. To this end, we present the results of a post-hoc self-assessment to evaluate the trustworthiness of an AI system for predicting a multiregional score conveying the degree of lung compromise in COVID-19 patients, developed and verified by an interdisciplinary team with members from academia, public hospitals, and industry in time of pandemic. The AI system aims to help radiologists to estimate and communicate the severity of damage in a patient's lung from Chest X-rays. It has been experimentally deployed in the radiology department of the ASST Spedali Civili clinic in Brescia, Italy, since December 2020 during pandemic time. The methodology we have applied for our post-hoc assessment, called Z-Inspection®, uses sociotechnical scenarios to identify ethical, technical, and domain-specific issues in the use of the AI system in the context of the pandemic.

Extracorporeal membrane oxygenation rewarming in the ED: an opportunity for success.

On average, approximately 1300 Americans die of hypothermia each year. Although accidental hypothermia is commonly associated with severely cold regions or mountain accident victims, hypothermia also commonly occurs in urban centers. Contributing factors often include homelessness, mental illness, and substance abuse. Hypothermia can profoundly affect the cardiovascular system. As the myocardium cools, the conduction system slows down,which results in prolongation of the QT interval as well as propensity for arrhythmias. Eventually, bradycardia, atrial fibrillation, and ventricular fibrillation (VF) can develop. The risk of cardiac arrest increases as the core temperature drops below 32°C and increases substantially when less than 28°C.

Elastic stable intramedullary nailing of tibial shaft fractures in children.

Most pediatric tibia shaft fractures are amenable to nonoperative treatment with satisfying results, yet surgical stabilization is necessary in certain cases. The purpose of our study was to determine the effectiveness and the complications associated with elastic stable intramedullary nailing in severe pediatric tibial fractures. We retrospectively reviewed 24 tibia shaft fractures in 24 patients that were treated operatively by elastic stable intramedullary nailing between 1997 and 2005 at our institution. Extensive review of all charts and radiographic data was completed at Cincinnati Children's Hospital Medical Center. There were 8 closed and 16 open fractures. The average union time for all tibia fractures was 20.4 weeks. The average union time for closed and open fractures was 21.5 and 20.2 weeks, respectively. Complications include 2 (8%) neurovascular, 2 (8%) infections, 2 (8%) malunions, and 1 (4%) leg-length discrepancy. Although complications do exist, elastic stable intramedullary nailing of pediatric tibia shaft fractures using Nancy nails is an effective treatment option.

Care of the HIV-positive patient in the emergency department in the era of highly active antiretroviral therapy.

More than 1 million individuals in the United States are HIV positive, with greater than 40,000 new patients being diagnosed per year. With the advent of highly active antiretroviral therapy (HAART), HIV-infected patients in the United States are living longer. HIV-infected patients receiving HAART now more commonly have noninfectious and nonopportunistic complications of their disease. This review article will discuss the assessment and treatment of HIV-positive patients in the era of HAART, with an emphasis on the noninfectious and changing infectious complications that require emergency care.