Narrow Results

Purpose: During the current pandemic scientists, researchers, and health professionals across the globe are in search of new technological methods for tackling COVID-19. The magnificent performance reported by machine learning and deep learning methods in the previous epidemic has encouraged researchers to develop systems with these methods to diagnose COVID-19.

Methods: In this paper, an ensemble-based multi-level voting model is proposed to diagnose COVID-19 from chest x-rays. The multi-level voting model proposed in this paper is built using four machine learning algorithms namely Random Forest (RF), Logistic Regression (LR), Support Vector Machine (SVM) with a linear kernel, and K-Nearest Neighbor (KNN). These algorithms are trained with features extracted using the ResNet50 deep learning model before merging them to form the voting model. In this work, voting is performed at two levels, at level 1 these four algorithms are grouped into 2 sets consisting of two algorithms each (set 1 — SVM with linear kernel and LR and set 2 — RF and KNN) and intra set hard voting is performed. At level 2 these two sets are merged using hard voting to form the proposed model.

Results: The proposed multilevel voting model outperformed all the machine learning algorithms, pre-trained models, and other proposed works with an accuracy of 100% and specificity of 100%.

Conclusion: The proposed model helps for the faster diagnosis of COVID-19 across the globe.

Binding site prediction for new proteins is important in structure-based drug design. The identified binding sites may be helpful in the development of treatments for new viral outbreaks in the world when there is no information available about their pockets with COVID-19 being a case in point. Identification of the pockets using computational methods, as an alternative method, has recently attracted much interest. In this study, the binding site prediction is viewed as a semantic segmentation problem. An improved 3D version of the U-Net model based on the dice loss function is utilized to predict the binding sites accurately. The performance of the proposed model on the independent test datasets and SARS-COV-2 shows the segmentation model could predict the binding sites with a more accurate shape than the recently published deep learning model, i.e. DeepSite. Therefore, the model may help predict the binding sites of proteins and could be used in drug design for novel proteins.

COVID-19 is a serious respiratory disease caused by a devastating coronavirus family (2019-nCoV) that has become a global epidemic. It is an infectious virus transmitted by inhalation or contact with the droplet core produced by infected people when they sneeze, cough, and speak. SARS-COV-2 transmission in the air is possible even in a confined space near the infected person. This study examines air conditioners’ effect on the mixed virus and droplets with aerosol disinfectant and gets throughout the elevator to detect the SARS-COV-2, which helps protect passengers’ lives. This study uses fluent 2019R3 software to simulate the virus transmission to model the transient flows numerically. The analysis found that the ventilation system’s turbulent fields can be an effective method of protecting the space from being saturated by the coronavirus.

Background: Management of hand trauma has evolved to incorporate assessment, treatment and rehabilitation of patients in a ‘one-stop’ clinic on initial presentation. Our aim was to evaluate the effect of coronavirus disease 2019 (COVID-19) on the choice of treatment for hand fractures using inter-rater agreement between surgeons.

Methods: All patients with hand fractures during the COVID-19 lockdown from March to May 2020 were included in the study. Two experienced hand surgeons blinded to management and outcomes independently reviewed radiographic images and relevant clinical history to provide their opinion on optimal treatment. Weighted kappa analysis was performed to determine concordance and inter-rater agreement between the two surgeons and actual management.

Results: The study included 82 patients (62 men and 20 women) with a mean age of 40.3 (SD 19.7). The injuries occurred most often at home following an accident (34%) or a fall (28%). Fractures involved the metacarpals in 29 patients and the distal phalanx in 22 patients. Thirty-five patients underwent surgery, whereas 47 were managed conservatively. Overall agreement between actual management and consultant A and consultant B was moderate (κ = 0.55, p < 0.0001 and κ = 0.63, p < 0.0001, respectively). Subgroup analysis showed a weak agreement between actual management of metacarpal fractures and consultant A and consultant B (κ = 0.22, p = 0.29 and κ = 0.47, p = 0.02, respectively). Inter-rater agreement was substantial for management of metacarpal fractures (κ = 0.73, p < 0.0001), but weak for distal phalanx fractures (κ = 0.29, p = 0.03).

Conclusion: Our study has shown that overall management of hand fractures remained optimised throughout the pandemic. However, a lack of concordance was observed in the management of metacarpals.

Level of Evidence: Level IV (Therapeutic)