Real-Time Arabic Sign Language Recognition Using a Hybrid Deep Learning Model.

Sign language is an essential means of communication for individuals with hearing disabilities. However, there is a significant shortage of sign language interpreters in some languages, especially in Saudi Arabia. This shortage results in a large proportion of the hearing-impaired population being deprived of services, especially in public places. This paper aims to address this gap in accessibility by leveraging technology to develop systems capable of recognizing Arabic Sign Language (ArSL) using deep learning techniques. In this paper, we propose a hybrid model to capture the spatio-temporal aspects of sign language (i.e., letters and words). The hybrid model consists of a Convolutional Neural Network (CNN) classifier to extract spatial features from sign language data and a Long Short-Term Memory (LSTM) classifier to extract spatial and temporal characteristics to handle sequential data (i.e., hand movements). To demonstrate the feasibility of our proposed hybrid model, we created a dataset of 20 different words, resulting in 4000 images for ArSL: 10 static gesture words and 500 videos for 10 dynamic gesture words. Our proposed hybrid model demonstrates promising performance, with the CNN and LSTM classifiers achieving accuracy rates of 94.40% and 82.70%, respectively. These results indicate that our approach can significantly enhance communication accessibility for the hearing-impaired community in Saudi Arabia. Thus, this paper represents a major step toward promoting inclusivity and improving the quality of life for the hearing impaired.

Intracerebral haemorrhage in multiple sclerosis: assessing the impact of disease-modifying medications.

Multiple Sclerosis (MS) is a complex autoimmune disorder that significantly impacts the central nervous system, leading to a range of complications. While intracranial haemorrhage (ICH) is a rare but highly morbid complication, more common CNS complications include progressive multifocal leukoencephalopathy (PML) and other CNS infections. This severe form of stroke, known for its high morbidity and mortality rates, presents a critical challenge in the management of MS. The use of disease-modifying drugs (DMDs) in treating MS introduces a nuanced aspect to patient care, with certain medications like Dimethyl Fumarate and Fingolimod showing potential in reducing the risk of ICH, while others such as Alemtuzumab and Mitoxantrone are associated with an increased risk. Understanding the intricate relationship between these DMDs, the pathophysiological mechanisms of ICH, and the individualised aspects of each patient's condition is paramount. Factors such as genetic predispositions, existing comorbidities, and lifestyle choices play a crucial role in tailoring treatment approaches, emphasising the importance of a personalised, vigilant therapeutic strategy. The necessity for ongoing and detailed research cannot be overstated. It is crucial to explore the long-term effects of DMDs on ICH occurrence and prognosis in MS patients, aiming to refine clinical practices and promote patient-centric, informed therapeutic decisions. This approach ensures that the management of MS is not only comprehensive but also adaptable to the evolving understanding of the disease and its treatments.

Pathobiology of Cutaneous Manifestations Associated with COVID-19 and Their Management.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) causing coronavirus disease 2019 (COVID-19) has been a rising concern since its declaration as a pandemic by the World Health Organization on 11 March 2020. Recently, its association with multiple underlying organs has been identified that includes cardiac, renal, gastrointestinal, nervous systems, and cutaneous manifestations. Cutaneous COVID-19 findings have been supposedly classified into the following categories: vesicular (varicella-like), papulo-vesiculsar, chilblains-like ("COVID toes") maculopapular, and urticarial morphologies. In this review, we aim to focus on the proposed pathophysiology behind the various dermatological manifestations associated with COVID-19 and their associated management. We also included prevalence and clinical features of the different COVID-19-related skin lesions in our review. A comprehensive narrative review of the literature was performed in PubMed databases. Data from case reports, observational studies, case series, and reviews till June 2022 were all screened and included in the review.

Dynamic Data Streams for Time-Critical IoT Systems in Energy-Aware IoT Devices Using Reinforcement Learning.

Thousands of energy-aware sensors have been placed for monitoring in a variety of scenarios, such as manufacturing, control systems, disaster management, flood control and so on, requiring time-critical energy-efficient solutions to extend their lifetime. This paper proposes reinforcement learning (RL) based dynamic data streams for time-critical IoT systems in energy-aware IoT devices. The designed solution employs the Q-Learning algorithm. The proposed mechanism has the potential to adjust the data transport rate based on the amount of renewable energy resources that are available, to ensure collecting reliable data while also taking into account the sensor battery lifetime. The solution was evaluated using historical data for solar radiation levels, which shows that the proposed solution can increase the amount of transmitted data up to 23%, ensuring the continuous operation of the device.

Evaluation of serum mesothelin in malignant and benign ovarian masses.

PURPOSE: To evaluate the diagnostic accuracy of serum mesothelin levels in patients with ovarian masses in comparison to serum cancer antigen (CA) 125 levels. METHODS: This diagnostic accuracy study was conducted in a gynecological oncology unit at Ain Shams University Maternity hospital. Based on radiological and clinical findings, a total of 110 patients were consecutively recruited. Preoperative serum mesothelin levels were assessed using enzyme-linked immunosorbent assay (ELISA) technique, while CA125 levels were determined using electrochemiluminescence immunoassay. All patients underwent exploratory laparotomy. Preoperative serum levels of both markers were correlated to histopathological reports obtained from each patient. RESULTS: A total of 96 patients were finally analyzed. Of the included 96 patients, 58 (60.4 %) had a benign ovarian lesion, while 38 (39.6 %) had a malignant lesion. The median serum CA125 levels were significantly higher in patients with malignant ovarian lesions than in patients with benign ovarian lesions [335.5 mIU/mL (range 60-1,127 mIU/mL) versus 33.65 mIU/mL (range 10.36-174 mIU/mL), P < 0.001]. The median serum mesothelin level was significantly higher in patients with malignant ovarian lesions than in patients with benign ovarian lesions [104.1 nmol/L (range 6.5-215.4 nmol/L) versus 12.65 nmol/L (range 6.5-102 nmol/L), P < 0.001]. The diagnostic sensitivity and specificity for mesothelin and CA125 were 97.4 and 98.3 % and 97.4 and 56.9 %, respectively. The combination of mesothelin with CA125 did not add predictive value to mesothelin compared with mesothelin alone [same sensitivity (97.4 %) and same specificity (98.3 %)]. Serum mesothelin levels rather than serum CA125 levels were a significant predictor of early-stage ovarian malignancy [Area under the curve = 0.732, 95 % confidence interval (0.543-0.921), P = 0.031]. CONCLUSION: In ovarian cancer, mesothelin seemed to have the same sensitivity, but a higher specificity than CA125. Combination of mesothelin and CA125 had no advantage over mesothelin alone. Mesothelin rather than CA125 was a significant predictor of early-stage ovarian cancer (stage I/II).