ALFABETO: Supporting COVID-19 hospital admissions with Bayesian Networks

The ongoing pandemics of coronavirus disease has accelerated the implementation of machine learning methods (ML) to support clinical decisions. Within this context, we present the ALFABETO project, whose aim is to aid clinicians during COVID-19 patients hospital admission through the application of ML approaches exploiting clinical and chest x-ray features. Yet, non linear ML classifiers are often perceived as not easily interpretable by users, thus hampering trust in ML predictions. Moreover, these ML models, such as Neural Networks or Random Forest, are not able to include pre-exisisting knowledge about a specific domain and are not designed to find causal relationships between variables. For these reasons, we wanted to investigate if Bayesian Networks were able to properly describe the hospital admission decision process. Bayesian Networks are probabilistic graphical models representing a set of variables and their conditional dependencies. The network structure was derived both from existing medical knowledge and from patients data collected during the first wave of the pandemic. While being explainable, we show that the Bayesian network has similar performance when compared to a less explainable ML model and that was able to generalize well across COVID-19 waves. © 2021 Copyright for this paper by its authors.

Subclinical pericarditis long after SARS-CoV-2 infection: A case report

We describe a rare complication of COVID-19 long after infection in a 76-years-old man presented to the Emergency Department with dyspnea and palpitations. A 12-lead Electrocardiogram (ECG) showed sinus tachycardia PR depression in the inferior leads associated with an apparent pseudo ST elevation. In the absence of elevation of inflammatory indices, considering the lack of symptoms neither NSAIDs nor colchicine were prescribed, and the patient was referred for clinical follow-up. After ten days ECG documented initial reduction of the widespread concave STE and PR depression, and the 1-month follow-up visit, the patient was asymptomatic with unremarkable physical examination, and a 12-lead ECG showed almost complete normalization of the ST and PR segments. Although pericardial involvement after COVID-19 infection has been already described, the incidence of subclinical pericarditis has not and may have implications for the monitoring of patients with uncomplicated COVID-19 infection managed as outpatients.

The role of emergency medicine residents during the global SARS-Cov-2 pandemic: The Pavia experience

In late January 2020, the first cases of Covid-19 were diagnosed in Italy. A month later the epidemic broke out in Lombardy bringing along dire consequences. Up to January 23rd 2021, the region counted 522,000 cases, and 26.518 deaths on a population of nearly 10 million. For many weeks thereafter tens of emergency COVID-19 patients were admitted every day through the ED requiring further adjustments in the organization of the Hospital, always in close cooperation with the out-of-hospital Emergency network. Among these, important and time-sensitive changes took place in the role of Residents in Emergency Medicine. As residents who worked through the first and second wave of the Sars-CoV-2 pandemic in the Emergency Department, we would like to discuss the consequences of our massive involvement on the front line of the healthcare effort to fight it.