Tracking and predicting COVID-19 radiological trajectory on chest X-rays using deep learning.

Radiological findings on chest X-ray (CXR) have shown to be essential for the proper management of COVID-19 patients as the maximum severity over the course of the disease is closely linked to the outcome. As such, evaluation of future severity from current CXR would be highly desirable. We trained a repurposed deep learning algorithm on the CheXnet open dataset (224,316 chest X-ray images of 65,240 unique patients) to extract features that mapped to radiological labels. We collected CXRs of COVID-19-positive patients from an open-source dataset (COVID-19 image data collection) and from a multi-institutional local ICU dataset. The data was grouped into pairs of sequential CXRs and were categorized into three categories: 'Worse', 'Stable', or 'Improved' on the basis of radiological evolution ascertained from images and reports. Classical machine-learning algorithms were trained on the deep learning extracted features to perform immediate severity evaluation and prediction of future radiological trajectory. Receiver operating characteristic analyses and Mann-Whitney tests were performed. Deep learning predictions between "Worse" and "Improved" outcome categories and for severity stratification were significantly different for three radiological signs and one diagnostic ('Consolidation', 'Lung Lesion', 'Pleural effusion' and 'Pneumonia'; all P < 0.05). Features from the first CXR of each pair could correctly predict the outcome category between 'Worse' and 'Improved' cases with a 0.81 (0.74-0.83 95% CI) AUC in the open-access dataset and with a 0.66 (0.67-0.64 95% CI) AUC in the ICU dataset. Features extracted from the CXR could predict disease severity with a 52.3% accuracy in a 4-way classification. Severity evaluation trained on the COVID-19 image data collection had good out-of-distribution generalization when testing on the local dataset, with 81.6% of intubated ICU patients being classified as critically ill, and the predicted severity was correlated with the clinical outcome with a 0.639 AUC. CXR deep learning features show promise for classifying disease severity and trajectory. Once validated in studies incorporating clinical data and with larger sample sizes, this information may be considered to inform triage decisions.

How COVID-19 Will Shape Urban Mobility

This document examines travel behavior during the COVID-19 lockdown and anticipated travel behavior over the short term and medium term (12-18 months from now with a possible vaccine in place). It is based on a survey conducted in April 2020 of 5,000 respondents from major cities in China, Western Europe, and the U.S. It begins with a look at the use of transportation modes during lockdown. During lockdown the use of most transportation modes declined. For the short-term, after lock-down, respondents expected to increase their walking, bicycling, or driving their own car and to use public transit and shared-mobility modes less frequently. In fact, more than 60% of Chinese respondents said that post-lockdown they were more likely to purchase an automobile. In the medium term, respondents say their use of public transit and shared mobility will increase. The authors present two scenarios, one featuring a resurgence of private car use and one featuring the return of public transit and micromobility use (the more likely scenario per the authors). The report concludes with actions that mobility providers, cities and policymakers, and investors could take to restore public transit ridership and the use of mobility services.

Outcomes and clinical practice in patients with COVID-19 admitted to the intensive care unit in Montréal, Canada: a descriptive analysis.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic is responsible for millions of infections worldwide, and a substantial number of these patients will be admitted to the intensive care unit (ICU). Our objective was to describe the characteristics, outcomes and management of critically ill patients with COVID-19 pneumonia at a single designated pandemic centre in Montréal, Canada. METHODS: A descriptive analysis was performed on consecutive critically ill patients with COVID-19 pneumonia admitted to the ICU at the Jewish General Hospital, a designated pandemic centre in Montréal, between Mar. 5 and May 21, 2020. Complete follow-up data corresponding to death or discharge from hospital health records were included to Aug. 4, 2020. We summarized baseline characteristics, management and outcomes, including mortality. RESULTS: A total of 106 patients were included in this study. Twenty-one patients (19.8%) died during their hospital stay, and the ICU mortality was 17.0% (18/106); all patients were discharged home or died, except for 4 patients (2 awaiting a rehabilitation bed and 2 awaiting long-term care). Twelve of 65 patients (18.5%) requiring mechanical ventilation died. Prone positioning was used in 29 patients (27.4%), including in 10 patients who were spontaneously breathing; no patient was placed on extracorporeal membrane oxygenation. High-flow nasal cannula was used in 51 patients (48.1%). Acute kidney injury was the most common complication, seen in 20 patients (18.9%), and 12 patients (11.3%) required renal replacement therapy. A total of 53 patients (50.0%) received corticosteroids. INTERPRETATION: Our cohort of critically ill patients with COVID-19 had lower mortality than that previously described in other jurisdictions. These findings may help guide critical care decision-making in similar health care systems in further COVID-19 surges.