Background: Predicting or diagnosing underlying kidney disease by analyzing whole urine remains the mainstay of nephrology practice. However, whole urine is a poor compartment to assess many structural changes in the kidney because whole urine contains only a few proteins derived from the kidney itself. Urinary exosomes, on the other hand, which are derived from the kidney, contain proteins secreted by the kidney. We experimentally tested the hypothesis that ‘urinary exosomes more faithfully represent changes in the kidney tissue than whole urine'. A direct comparison between whole urine and urine exosomal levels of two chosen kidney disease markers, gelatinase and ceruloplasmin, was carried out on diabetic kidney disease patients. Methods: Urinary exosomes were separated from whole urine by sequential centrifugation including ultra-centrifugation. Gelatinase activity was measured using fluorosceinated gelatin as the substrate, and ceruloplasmin was measured by sandwich ELISA. A few kidney specimens from patients biopsied for atypical features were histochemically stained for validation of the biochemical results. Results: We found that changes in both, gelatinase (decreased activity) and ceruloplasmin (increased levels), in the urinary exosomes of diabetic kidney patients were in agreement with the alterations of these two proteins in the kidney tissue. In contrast, the levels of these two proteins in whole urine were highly variable and did not correlate with levels in the diabetic kidney tissue. Conclusion: In conclusion, these results confirmed our hypothesis that protein markers in urinary exosomes better reflected the underlying protein changes in the kidney than in whole urine samples.

No abstract

No abstract

ObjectivesThere exists a wide gap in the availability of mechanical ventilator devices and their acute need in the context of the COVID-19 pandemic. An initial triaging method that accurately identifies the need for mechanical ventilation in hospitalised patients with COVID-19 is needed. We aimed to investigate if a potentially deteriorating clinical course in hospitalised patients with COVID-19 can be detected using all X-ray images taken during hospitalisation.MethodsWe exploited the well-established DenseNet121 deep learning architecture for this purpose on 663 X-ray images acquired from 528 hospitalised patients with COVID-19. Two Pulmonary and Critical Care experts blindly and independently evaluated the same X-ray images for the purpose of validation.ResultsWe found that our deep learning model predicted the need for mechanical ventilation with a high accuracy, sensitivity and specificity (90.06%, 86.34% and 84.38%, respectively). This prediction was done approximately 3 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%.ConclusionsOur deep learning model accurately predicted the need for mechanical ventilation early during hospitalisation of patients with COVID-19. Until effective preventive or treatment measures become widely available for patients with COVID-19, prognostic stratification as provided by our model is likely to be highly valuable.

No abstract