Multimodal deep learning for COVID-19 prognosis prediction in the emergency department: a bi-centric study. (preprint)

Clinical deterioration of COVID-19 patients is still a challenging event to predict in the emergency department (ED). The present study developed an artificial neural network using textual and tabular data from ED electronic medical reports. Predicted outcomes were 30-day mortality and ICU admission. Consecutive patients between February 20 and May 5, 2020, from Humanitas Research Hospital and San Raffaele Hospital, in the Milan area, were included. COVID-19 patients were 1296. Textual predictors were patient history, physical exam, and radiological reports. Tabular predictors were age, creatinine, C-reactive protein, hemoglobin, and platelet count. Tabular-textual model performance indices were compared to a model implementing only tabular data. For 30-day mortality, the combined model yielded slightly better performances than the tabular model, with AUC 0.84 ± 0.02, F-1 score 0.56 ± 0.04 and an MCC 0.44 ± 0.04. Tabular model performance was: AUC 0.84 ± 0.02, F-1 score 0.55 ± 0.03 and MCC 0.43 ± 0.04. As for ICU admission, the combined model was not superior to the tabular one.  The present data points to the effectiveness of a textual and tabular model for COVID-19 prognosis prediction. Also, it may support the ED physician in their decision-making process.

Waiting for the Second (Non)-Covid-19 Wave: Variations in Volume of Emergency Surgeries and of Emergency Department Accesses in a Third Level Hospital in Milan, Lombardy, During the Outbreak (preprint)

Introduction: During the recent outbreak of COVID-19 (Corona VIrus Diseases 2019), Lombardy was the Italian region most affected, with 87,000 patients and 15,876 deaths (until May 26). Since February 22, well before the Government declared the state of emergency, a huge reduction of emergency surgeries was seen in Lombardy Hospitals, with a generalized drop of attendances in the Emergency Departments (EDs).Study Objective: The aim of this study is to report the experience of the ED of a third-level hospital in downtown Milan, Lombardy (IRCCS Foundation Cà Granda Ospedale Maggiore Policlinico), and try to explain the causes of the observed phenomena.Methods: A retrospective, observational study was performed assessing the volume of emergency surgeries and of the attendances in the ED during the course of the pandemic, i.e. immediately before, during and after progressive community lockdown in response to the COVID-19 pandemic, comparing the same time periods in 2019.Results: Compared to the previous year, in 2020 a significant overall drop of emergency surgeries (60%, p<0.002) and of ED attendances (66%, p≅0) was observed. The drop was significant for medical ( 40%), surgical (74%), specialist fast track (92%), and psychiatric (60%) complaints, for domestic violence accesses (59%) and for patients who left the ED without being seen (LWBS) (76%). Conversely, deaths raised by 196%.Conclusion: During the COVID-19 outbreak the volume of urgent surgeries and the volume of patients accessing ED dropped. At the moment, it is not known if mortality of people who did not seek care increased during the pandemic. Further studies are needed to try to understand if such reductions during the COVID-19 pandemic will result in a rebound of patients left untreated, or in unwanted consequences on population health.