StackNet-DenVIS: a multi-layer perceptron stacked ensembling approach for COVID-19 detection using X-ray images.

The highly contagious nature of Coronavirus disease 2019 (Covid-19) resulted in a global pandemic. Due to the relatively slow and taxing nature of conventional testing for Covid-19, a faster method needs to be in place. The current researches have suggested that visible irregularities found in the chest X-ray of Covid-19 positive patients are indicative of the presence of the disease. Hence, Deep Learning and Image Classification techniques can be employed to learn from these irregularities, and classify accordingly with high accuracy. This research presents an approach to create a classifier model named StackNet-DenVIS which is designed to act as a screening process before conducting the existing swab tests. Using a novel approach, which incorporates Transfer Learning and Stacked Generalization, the model aims to lower the False Negative rate of classification compensating for the 30% False Negative rate of the swab tests. A dataset gathered from multiple reliable sources consisting of 9953 Chest X-rays (868 Covid and 9085 Non-Covid) was used. Also, this research demonstrates handling data imbalance using various techniques involving Generative Adversarial Networks and sampling techniques. The accuracy, sensitivity, and specificity obtained on our proposed model were 95.07%, 99.40% and 94.61% respectively. To the best of our knowledge, the combination of accuracy and false negative rate obtained by this paper outperforms the current implementations. We must also highlight that our proposed architecture also considers other types of viral pneumonia. Given the unprecedented sensitivity of our model we are optimistic it contributes to a better Covid-19 detection.

Lingual traction to facilitate fiber-optic intubation of difficult airways: a single-anesthesiologist randomized trial.

PURPOSE: Flexible fiber-optic bronchoscope-guided orotracheal intubation is a valuable technique with demonstrated benefits in the management of difficult airways. Despite its popularity with anesthesia providers, the technique is not fail-safe and airway-related complications secondary to failed intubation attempts remain an important problem. We sought to determine the effect of incorporating lingual traction on the success rate of fiber-optic bronchoscope-guided intubation in patients with anticipated difficult airways. METHODS: In this prospective, randomized, cohort study, we enrolled 91 adult patients with anticipated difficult airways scheduled for elective surgery to undergo fiber-optic bronchoscope-guided orotracheal intubation alone or with lingual traction by an individual anesthesiologist after induction of general anesthesia and neuromuscular blockade. A total of 78 patients were randomized: 39 patients to the fiber-optic bronchoscope-guided intubation with lingual traction group and 39 patients to the fiber-optic bronchoscope-guided intubation alone group. The primary endpoint was the rate of successful first attempt intubations. The secondary outcome was sore throat grade on post-operative day 1. RESULTS: Fiber-optic intubation with lingual traction compared to fiber-optic intubation alone resulted in a higher success rate (92.3 vs. 74.4 %, χ (2) = 4.523, p = 0.033) and greater odds for successful first attempt intubation (OR 4.138, 95 % CI 1.041-16.444, p = 0.044). Sore throat severity on post-operative day 1 was not significantly different but trended towards worsening grades with lingual traction. CONCLUSIONS: In this study, lingual traction was shown to be a valuable maneuver for facilitating fiber-optic bronchoscope-guided intubation in the management of patients with anticipated difficult airways.