Magnetic Resonance Imaging Features of Rhino-Orbito-Cerebral Mucormycosis in Post-COVID-19 Patients: Radio-Pathological Correlation.

There has been a notable increase in rhino-orbito-cerebral mucormycosis (ROCM) post-coronavirus disease 2019 (COVID-19), which is an invasive fungal infection with a fatal outcome. Magnetic resonance imaging (MRI) is a valuable tool for early diagnosis of ROCM and assists in the proper management of these cases. This study aimed to describe the characteristic MRI findings of ROCM in post-COVID-19 patients to help in the early diagnosis and management of these patients. This retrospective descriptive study was conducted at a single hospital and included 52 patients with COVID-19 and a histopathologically proven ROCM infection who were referred for an MRI of the paranasal sinuses (PNS) due to sino-orbital manifestations. Two radiologists reviewed all the MR images in consensus. The diagnosis was confirmed by histopathological examination. The maxillary sinus was the most commonly affected PNS (96.2%). In most patients (57.7%), multiple sinuses were involved with the black turbinate sign on postcontrast images. Extrasinus was evident in 43 patients with orbital involvement. The pterygopalatine fossa was involved in four patients. Three patients had cavernous sinus extension, two had pachymeningeal enhancement, and one had epidural collection. The alveolar margin was affected in two patients, and five patients had an extension to the cheek. The awareness of radiologists by the characteristic MRI features of ROCM in post-COVID-19 patients helps in early detection, early proper management, and prevention of morbid complications.

Medical imaging in problem-based learning and impact on the students: A cross-sectional study.

OBJECTIVE: To investigate the medical students' performance with and perception towards different multimedia medical imaging tools. METHODS: The cross-sectional study was conducted at the College of Medicine, Qassim University, Saudi Arabia, from 2019 to 2020, and comprised third year undergraduate medical students during the academic year 2019-2020. The students were divided into tow groups. Those receiving multimedia-enhanced problem-based learning sessions were in intervention group A, while those receiving traditional problem-based learning sessions were in control group B. Scores of the students in the formative assessment at the end of the sessions were compared between the groups. Students' satisfaction survey was also conducted online and analysed. Data was analysed using SPSS 21. RESULTS: Of the 130 medical students, 75(57.7%) were males and 55(42.3%) were females. A significant increase in the mean scores was observed for both male and female students in group A compared to those in group B (p<0.05). The perception survey was filled up by 100(77%) students, and open-ended comments were obtained from 88(88%) of them. Overall, 69(74%) subjects expressed satisfaction with the multimedia-enhanced problem-based learning sessions. CONCLUSIONS: Radiological and pathological images enhanced the students' understanding, interaction and critical thinking during problem-based learning sessions.

A Turf-Based Feature Selection Technique for Predicting Factors Affecting Human Health during Pandemic.

Worldwide, COVID-19 is a highly contagious epidemic that has affected various fields. Using Artificial Intelligence (AI) and particular feature selection approaches, this study evaluates the aspects affecting the health of students throughout the COVID-19 lockdown time. The research presented in this paper plays a vital role in indicating the factor affecting the health of students during the lockdown in the COVID-19 pandemic. The research presented in this article investigates COVID-19's impact on student health using feature selections. The Filter feature selection technique is used in the presented work to statistically analyze all the features in the dataset, and for better accuracy. ReliefF (TuRF) filter feature selection is tuned and utilized in such a way that it helps to identify the factors affecting students' health from a benchmark dataset of students studying during COVID-19. Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Support Vector Machine (SVM), and 2- layer Neural Network (NN), helps in identifying the most critical indicators for rapid intervention. Results of the approach presented in the paper identified that the students who maintained their weight and kept themselves busy in health activities in the pandemic, such student's remained healthy through this pandemic and study from home in a positive manner. The results suggest that the 2- layer NN machine-learning algorithm showed better accuracy (90%) to predict the factors affecting on health issues of students during COVID-19 lockdown time.

Analyzing the Features Affecting the Performance of Teachers during Covid-19: A Multilevel Feature Selection

COVID-19 is a profoundly contagious pandemic that has taken the world by storm and has afflicted different fields of life with negative effects. It has had a substantial impact on education which is evident from the transition from Face-to-Face (F2F) teaching to online mode of education and the rigid implementation of lockdown across the globe. This study examines the factors impacting the performance of teachers during the lockdown period of COVID-19 using various feature selection algorithms and Artificial Intelligence techniques. In this paper, we have proposed a novel multilevel feature selection for the prediction of the factors affecting the teachers’ satisfaction with online teaching and learning in COVID-19. The proposed multilevel feature selection is composed of the Fast Correlation Based Filter (FCBF), Mutual Information (MI), Relieff, and Particle Swarm Optimization (PSO) feature selection. The performance of the proposed feature selection approach is evaluated through the teachers’ benchmark dataset. We used a range of measures like accuracy, precision, f-measure, and recall to evaluate the performance of the proposed approach. We applied different machine learning approaches (SVM, LGBM, and ANN) with the proposed multilevel feature selection technique. The performance of the proposed approach is also compared with existing feature selection algorithms, and the results show the improvement in the performance of feature selection in terms of accuracy, precision, recall, and F-Measure. Proposed feature selection provides more than 80% accuracy with Light Weight Gradient Boosting Machine (LGBM).