ASSOCIATION OF HYPERGLYCEMIA WITH HOSPITAL MORTALITY IN COVID-19 PATIENTS WITHOUT DIABETES: A COHORT STUDY (preprint)

Objective: Diabetes is a known risk factor for mortality in Coronavirus disease 2019 (COVID-19) patients. Our objective was to identify prevalence of hyperglycemia in COVID-19 patients with and without diabetes and quantify its association with COVID-19 disease course. Research Design and Methods: In this observational cohort study, all consecutive COVID-19 patients admitted to John H Stroger Jr. Hospital, Chicago, IL from March 15, 2020 to May 15, 2020 were included. The primary outcome was hospital mortality and the main predictor was hyperglycemia (any blood glucose [≥]7.78 mmol/L during hospitalization). Results: Of 403 COVID-19 patients studied, 228 (57%) developed hyperglycemia. Of these, 83 (21%) had hyperglycemia without diabetes. A total of 51 (12.7%) patients died. Compared to the reference group no-diabetes/no-hyperglycemia patients the no-diabetes/hyperglycemia patients showed higher mortality (1.8% versus 20.5%, adjusted odds ratio 21.94 (95% confidence interval 4.04-119.0), p < 0.001); improved prediction of death (p=0.0162) and faster progression to death (p=0.0051). Hyperglycemia within the first 24 and 48 hours was also significantly associated with mortality (odds ratio 2.15 and 3.31, respectively). Further, compared to the same reference group, no-diabetes/hyperglycemia patients had higher risk of ICU admission (p<0.001), mechanical ventilation (p<0.001) and acute respiratory distress syndrome (p<0.001) and a longer hospital stay in survivors (p<0.001). Conclusions: Hyperglycemia in the absence of diabetes was common (21% of hospitalized COVID-19 patients) and was associated with an increased risk of and faster progression to death. Development of hyperglycemia in COVID-19 patients who do not have diabetes is an early indicator of poor prognosis.

A DEEP LEARNING MODEL TO PREDICT THE NEED FOR MECHANICAL VENTILATION USING CHEST X-RAY IMAGES IN HOSPITALIZED COVID-19 PATIENTS (preprint)

PurposeEarly identification of a potentially deteriorating clinical course in hospitalized COVID-19 patients is critical since there exists a resource-demand gap for the ventilators. MaterialsWe aimed to develop and validate a deep learning-based approach to predict the need for mechanical ventilation as early as at the time of initial radiographic evaluation. We exploited the well-established DenseNet121 deep learning architecture for this purpose on 663 X-ray images derived from 528 hospitalized COVID-19 patients. Two Pulmonary and Critical Care experts blindly and independently evaluated the same X-ray images for purpose of validation. ResultsWe found that our deep learning model predicted the need for ventilation with a high accuracy, sensitivity and specificity (90.06%, 86.34% and 84.38%, respectively). This prediction was done approximately three days ahead of the actual intubation event. Our model also outperformed two Pulmonary and Critical Care experts who evaluated the same X-ray images and provided an incremental accuracy of 7.24-13.25%. ConclusionOur deep learning model accurately predicted the need for mechanical ventilation early during hospitalization of COVID-19 patients. Until effective preventive or treatment measures become widely available for COVID-19 patients, prognostic stratification as provided by our model is likely to be highly valuable.