COVID-19 Classification from X-Ray Images: An Approach to Implement Federated Learning on Decentralized Dataset

The COVID-19 pandemic has devastated our daily lives, leaving horrific repercussions in its aftermath. Due to its rapid spread, it was quite difficult for medical personnel to diagnose it in such a big quantity. Patients who test positive for Covid-19 are diagnosed via a nasal PCR test. In comparison, polymerase chain reaction (PCR) findings take a few hours to a few days. The PCR test is expensive, although the government may bear expenses in certain places. Furthermore, subsets of the population resist invasive testing like swabs. Therefore, chest X-rays or Computerized Vomography (CT) scans are preferred in most cases, and more importantly, they are non-invasive, inexpensive, and provide a faster response time. Recent advances in Artificial Intelligence (AI), in combination with state-of-the-art methods, have allowed for the diagnosis of COVID-19 using chest x-rays. This article proposes a method for classifying COVID-19 as positive or negative on a decentralized dataset that is based on the Federated learning scheme. In order to build a progressive global COVID-19 classification model, two edge devices are employed to train the model on their respective localized dataset, and a 3-layered custom Convolutional Neural Network (CNN) model is used in the process of training the model, which can be deployed from the server. These two edge devices then communicate their learned parameter and weight to the server, where it aggregates and updates the global model. The proposed model is trained using an image dataset that can be found on Kaggle. There are more than 13,000 X-ray images in Kaggle Database collection, from that collection 9000 images of Normal and COVID-19 positive images are used. Each edge node possesses a different number of images;edge node 1 has 3200 images, while edge node 2 has 5800. There is no association between the datasets of the various nodes that are included in the network. By doing it in this manner, each of the nodes will have access to a separate image collection that has no correlation with each other. The diagnosis of COVID-19 has become considerably more efficient with the installation of the suggested algorithm and dataset, and the findings that we have obtained are quite encouraging. © 2023 Tech Science Press. All rights reserved.

Kinetics of a Reaction-Diffusion Mtb/SARS-CoV-2 Coinfection Model with Immunity

The severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) and Mycobacterium tuberculosis (Mtb) coinfection has been observed in a number of nations and it is connected with severe illness and death. The paper studies a reaction–diffusion within-host Mtb/SARS-CoV-2 coinfection model with immunity. This model explores the connections between uninfected epithelial cells, latently Mtb-infected epithelial cells, productively Mtb-infected epithelial cells, SARS-CoV-2-infected epithelial cells, free Mtb particles, free SARS-CoV-2 virions, and CTLs. The basic properties of the model's solutions are verified. All equilibrium points with the essential conditions for their existence are calculated. The global stability of these equilibria is established by adopting compatible Lyapunov functionals. The theoretical outcomes are enhanced by implementing numerical simulations. It is found that the equilibrium points mirror the single infection and coinfection states of SARS-CoV-2 with Mtb. The threshold conditions that determine the movement from the monoinfection to the coinfection state need to be tested when developing new treatments for coinfected patients. The impact of the diffusion coefficients should be monitored at the beginning of coinfection as it affects the initial distribution of particles in space. © 2023 by the authors.

Best selected forecasting models for COVID-19 pandemic

This study sought to identify the most accurate forecasting models for COVID-19-confirmed cases, deaths, and recovered patients in Pakistan. For COVID-19, time series data are available from 16 April to 15 August 2021 from the Ministry of National Health Services Regulation and Coordination's health advice portal. Descriptive as well as time series models, autoregressive integrated moving average, exponential smoothing models (Brown, Holt, and Winters), neural networks, and Error, Trend, Seasonal (ETS) models were applied. The analysis was carried out using the R coding language. The descriptive analysis shows that the average number of confirmed cases, COVID-19-related deaths, and recovered patients reported each day were 2,916, 69.43, and 2,772, respectively. The highest number of COVID-19 confirmed cases and fatalities per day, however, were recorded on April 17, 2021 and April 27, 2021, respectively. ETS (M, N, M), neural network, nonlinear autoregressive (NNAR) (3, 1, 2), and NNAR (8, 1, 4) forecasting models were found to be the best among all other competing models for the reported confirmed cases, deaths, and recovered patients, respectively. COVID-19-confirmed outbreaks, deaths, and recovered patients were predicted to rise on average by around 0.75, 5.08, and 19.11% daily. These statistical results will serve as a guide for disease management and control.

The Role of Social Networks in Promoting Positive Behaviour during Covid-19 Crisis Amongst a Sample of Users in Saudi Society: Twitter as a Model

This study seeks analysing Twitter social network role in promoting positive behaviour during COVID-19 crisis and exploring the relationship between them. It targets identifying Twitter positive behaviour level differences through variables of gender, age, marital status, residence status, administrative region, and Twitter using size. An online questionnaire was used on a validity-and-stability verified sample of (586) individual Twitter users in the Kingdom of Saudi Arabia. Sample members approved Twitter users' positive behaviour during COVID-19 crisis. They agreed that the positive behaviour level was medium with a Twitter effect of (19.4%). There were both a positive, medium-strong correlation between Twitter daily use and a statistically significant correlation between one - session Twitter using and positive behaviour promotion. However, there were statistically significant differences in positive behaviour promotion when using Twitter between social status favouring singles, residence status favouring residents, age favouring those under 21, administrative region favouring the southern region, usage period favouring network daily and two days - users, and browsing time favouring much Twitter users.The study recommends conducting studies on positive social behaviour and its dimensions to broadly generalise results. Studies on the Internet of behaviour and artificial intelligence are needed to analyse the positive behaviour expected by social networks users to enhance opportunities. It also stressed children and adolescents' digital social education to prepare community members for effective online participation, the activation of public and private services-providing agencies Twitter accounts, interacting positively with users' questions and responses, and substituting fixed stereotypes by interesting interactive patterns.

COVID-19 among the Asymptomatic Healthcare Workers in the Tertiary Care Centers of the Southwestern Region of Saudi Arabia: Preventive and Protective Insights

Background: COVID-19 pandemic has sent serious waves of medical emergency all over the world. Healthcare workers (HCWs) are vulnerable to the infection through various patient care processes. As the pandemic advances, it becomes necessary to screen the asymptomatic HCWs for COVID-19 as they constitute potential sources for the disease transmission. Objectives: To screen for the incidence of COVID-19 among asymptomatic HCWs in the tertiary care centers in the Southern regions of Saudi Arabia using both RT-PCR and serology. Methods: A cross-sectional, hospital-based study was conducted to determine the incidence of COVID-19 among the asymptomatic HCWs using RT-PCR and serological assays among 186 consented participants. Results: The total number of COVID-19 cases among the participants using all tests was 34 (18.3%). Out of the total participants, 4.8%, 3.2%, 7%, 10.2%, and 11.8% positive COVID-19 cases were detected using RT-PCR, rapid ICT for IgG, rapid ICT for IgM, ELISA for IgG and ELISA for IgM respectively. Significantly higher cases were observed among HCWs in the ICU of Aseer Central Hospital. 100% of the medical students and administrative staff, 40% of respiratory therapists, 31.8% of laboratory specialists, 22.7% of cleaners, 13.5% of physicians, 12.2% of nurses participated were positive to COVID-19. Participants of 18-24 years old showed the highest level of cases. However, considering the total number of positive COVID-19, nurses showed the highest number of cases. Conclusions: Considerable number of COVID-19 cases were detected among HCWs in the Southern region of KSA. Screening of HCWs should have the priority in the preventive interventions.

Incidence risk and cumulative risk of COVID-19 infection among healthcare workers over the first year of the pandemic

Objectives: To analyze the spread rate and the cumulative risk of COVID-19 infection among healthcare workers (HCWs) over the first year of the pandemic. Method: An online, cross-sectional study involved HCWs who were in-service during the first year of COVID-19 crisis, including all healthcare institutions of Jeddah. History and date of COVID-19 infection were collected to estimate the COVID-19-free time, by reference to 03 March 2020, when the first case in Saudi Arabia was identified. Kaplan-Meier survival and Cox regression methods were used to analyze the cumulative risk of COVID-19 infection and the associated factors.

Drone-based AI/IoT Framework for Monitoring, Tracking and Fighting Pandemics

Since World Health Organization (WHO) has declared the Coronavirus disease (COVID-19) a global pandemic, the world has changed. All life’s fields and daily habits have moved to adapt to this new situation. According to WHO, the probability of such virus pandemics in the future is high, and recommends preparing for worse situations. To this end, this work provides a framework for monitoring, tracking, and fighting COVID-19 and future pandemics. The proposed framework deploys unmanned aerial vehicles (UAVs), e.g.;quadcopter and drone, integrated with artificial intelligence (AI) and Internet of Things (IoT) to monitor and fight COVID-19. It consists of two main systems;AI/IoT for COVID-19 monitoring and drone-based IoT system for sterilizing. The two systems are integrated with the IoT paradigm and the developed algorithms are implemented on distributed fog units connected to the IoT network and controlled by software-defined networking (SDN). The proposed work is built based on a thermal camera mounted in a face-shield, or on a helmet that can be used by people during pandemics. The detected images, thermal images, are processed by the developed AI algorithm that is built based on the convolutional neural network (CNN). The drone system can be called, by the IoT system connected to the helmet, once infected cases are detected. The drone is used for sterilizing the area that contains multiple infected people. The proposed framework employs a single centralized SDN controller to control the network operations. The developed system is experimentally evaluated, and the results are introduced. Results indicate that the developed framework provides a novel, efficient scheme for monitoring and fighting COVID-19 and other future pandemics. © 2022 Tech Science Press. All rights reserved.

Iot-based reusable medical suit for daily life use in the era of covid-19

Coronavirus disease (COVID-19) is a big problem that scares people all over the world. Life over the world has changed, new aspects for daily life have been introduced. A main problem with COVID-19 is the way it spreads. Covid-19 spreads, primarily, through contact with an infected person when they cough or sneeze, or with an infected surface. Thus, a novel way to make a protec-tion against COVID-19 is to stay away or make yourself isolated from infected people and surfaces. To this end, this work, mainly, aims to design and develop a novel auto-sterilized suit embedded with some medical sensors and other Internet of Things (IoT) devices to provide the required level of isolation, safety, tracking and monitoring of COVID-19 and other pandemic diseases. The developed suit is an auto-sterilized suit for medical purposes and for daily life use. The sterilizing process of the suit is controlled by the IoT paradigm to provide the required control and interface in an automated way. According to the location of the user, wearing the suit, an appropriate sterilizing mode is activated automa-tically and the suit is sterilized via distributed nozzles over the suit. Furthermore, the distributed medical sensors represent a wireless body area network (WBAN) that is integrated with an IoT gateway to provide periodic measures of medical healthcare parameters such as body temperature, breathing rate, oxygen saturation level and pulse rate. These measures are used to identify the user’s health and the probability of being infected by COVID-19. All measures are transferred to the remote IoT cloud to analyze these data and monitor people around the day. In case of unusual measures, users are moved among three databases associated with health, infected and properly infected users. The suit is under prototyping and the work is mainly introduced to present the design stages. © 2022, Tech Science Press. All rights reserved.

Classification Framework for COVID-19 Diagnosis Based on Deep CNN Models

Automated diagnosis based on medical images is a very promising trend in modern healthcare services. For the task of automated diagnosis, there should be flexibility to deal with an enormous amount of data represented in the form of medical images. In addition, efficient algorithms that could be adapted according to the nature of images should be used. The importance of automated medical diagnosis has been maximized with the evolution of COVID-19 pandemic. COVID-19 first appeared in China, Wuhan, and then it has exploded in the whole world with a very bad impact on our daily life. The third wave of COVID-19 in the third world is really a disaster in current days, especially with the emergence of the delta variant of COVID-19 that is widespread. Required inspections should be carried out to monitor the COVID-19 spread in daily life and allow primary diagnosis of suspected cases, and long-term clinical laboratory monitoring. Healthcare professionals or radiologists can exploit AI (Artificial Intelligence) tools to quickly and reliably identify the cases of COVID-19. This paper introduces a DCNN (Deep Convolutional Neural Network) framework for chest X-ray and CT image classification based on TL (Transfer Learning). The objective is to perform multi-class and binary classification of the images in order to determine pneumonia and COVID-19 case. The TL is feasible, when using a small dataset by transferring knowledge from natural image classification to medical image classification. Two types of TL are used. The first type is fine-tuning of the DenseNet121, Densenet169, DenseNet201, ResNet50, ResNet152, VGG16, and VGG19 models. The second type is deep tuning of the LeNet-5, AlexNet, Inception naive v1, and VGG16 models. Extensive tests have been carried out on datasets of chest X-ray and CT images with different training/testing ratios of 80%:20%, 70%:30%, and 60%:40%. Experimental results on 9,270 chest X-ray ray and 2,762 chest CT images acquired from different institutions show that the TL is effective with an average accuracy of 98.49%.

An efficient CNN-based hybrid classification and segmentation approach for COVID-19 detection

COVID-19 remains to proliferate precipitously in the world. It has significantly influenced public health, the world economy, and the persons’ lives. Hence, there is a need to speed up the diagnosis and precautions to deal with COVID-19 patients. With this explosion of this pandemic, there is a need for automated diagnosis tools to help specialists based on medical images. This paper presents a hybrid Convolutional Neural Network (CNN)-based classification and segmentation approach for COVID-19 detection from Computed Tomography (CT) images. The proposed approach is employed to classify and segment the COVID-19, pneumonia, and normal CT images. The classification stage is firstly applied to detect and classify the input medical CT images. Then, the segmentation stage is performed to distinguish between pneumonia and COVID-19 CT images. The classification stage is implemented based on a simple and efficient CNN deep learning model. This model comprises four Rectified Linear Units (ReLUs), four batch normalization layers, and four convolutional (Conv) layers. The Conv layer depends on filters with sizes of 64, 32, 16, and 8. A 2 × 2 window and a stride of 2 are employed in the utilized four max-pooling layers. A soft-max activation function and a Fully-Connected (FC) layer are utilized in the classification stage to perform the detection process. For the segmentation process, the Simplified Pulse Coupled Neural Network (SPCNN) is utilized in the proposed hybrid approach. The proposed segmentation approach is based on salient object detection to localize the COVID-19 or pneumonia region, accurately. To summarize the contributions of the paper, we can say that the classification process with a CNN model can be the first stage a highly-effective automated diagnosis system. Once the images are accepted by the system, it is possible to perform further processing through a segmentation process to isolate the regions of interest in the images. The region of interest can be assesses both automatically and through experts. This strategy helps so much in saving the time and efforts of specialists with the explosion of COVID-19 pandemic in the world. The proposed classification approach is applied for different scenarios of 80%, 70%, or 60% of the data for training and 20%, 30, or 40% of the data for testing, respectively. In these scenarios, the proposed approach achieves classification accuracies of 100%, 99.45%, and 98.55%, respectively. Thus, the obtained results demonstrate and prove the efficacy of the proposed approach for assisting the specialists in automated medical diagnosis services. © 2022 Tech Science Press. All rights reserved.

Deep Learning and Uniform LBP Histograms for Position Recognition of Elderly People with Privacy Preservation

For the elderly population, falls are a vital health problem especially in the current context of home care for COVID-19 patients. Given the saturation of health structures, patients are quarantined, in order to prevent the spread of the disease. Therefore, it is highly desirable to have a dedicated monitoring system to adequately improve their independent living and significantly reduce assistance costs. A fall event is considered as a specific and brutal change of pose. Thus, human poses should be first identified in order to detect abnormal events. Prompted by the great results achieved by the deep neural networks, we proposed a new architecture for image classification based on local binary pattern (LBP) histograms for feature extraction. These features were then saved, instead of saving the whole image in the series of identified poses. We aimed to preserve privacy, which is highly recommended in health informatics. The novelty of this study lies in the recognition of individuals' positions in video images avoiding the convolution neural networks (CNNs) exorbitant computational cost and Minimizing the number of necessary inputs when learning a recognition model. The obtained numerical results of our approach application are very promising compared to the results of using other complex architectures like the deep CNNs. © 2021. by the authors. All Rights Reserved.

Automated COVID-19 detection based on single-image super-resolution and CNN models

In developing countries, medical diagnosis is expensive and time consuming. Hence, automatic diagnosis can be a good cheap alternative. This task can be performed with artificial intelligence tools such as deep Convolutional Neural Networks (CNNs). These tools can be used on medical images to speed up the diagnosis process and save the efforts of specialists. The deep CNNs allow direct learning from the medical images. However, the accessibility of classified data is still the largest challenge, particularly in the field of medical imaging. Transfer learning can deliver an effective and promising solution by transferring knowledge from universal object detection CNNs to medical image classification. However, because of the inhomogeneity and enormous overlap in intensity between medical images in terms of features in the diagnosis of Pneumonia and COVID-19, transfer learning is not usually a robust solution. Single-Image Super-Resolution (SISR) can facilitate learning to enhance computer vision functions, apart from enhancing perceptual image consistency. Consequently, it helps in showing the main features of images. Motivated by the challenging dilemma of Pneumonia and COVID-19 diagnosis, this paper introduces a hybrid CNN model, namely SIGTra, to generate super-resolution versions of X-ray and CT images. It depends on a Generative Adversarial Network (GAN) for the super-resolution reconstruction problem. Besides, Transfer learning with CNN (TCNN) is adopted for the classification of images. Three different categories of chest X-ray and CT images can be classified with the proposed model. A comparison study is presented between the proposed SIGTra model and the other related CNN models for COVID-19 detection in terms of precision, sensitivity, and accuracy. © 2021 Tech Science Press. All rights reserved.

An efficient CNN-based automated diagnosis framework from COVID-19 CT images

Corona Virus Disease-2019 (COVID-19) continues to spread rapidly in the world. It has dramatically affected daily lives, public health, and the world economy. This paper presents a segmentation and classification framework of COVID-19 images based on deep learning. Firstly, the classification process is employed to discriminate between COVID-19, non-COVID, and pneumonia by Convolutional Neural Network (CNN). Then, the segmentation process is applied for COVID-19 and pneumonia CT images. Finally, the resulting segmented images are used to identify the infected region, whether COVID-19 or pneumonia. The proposed CNN consists of four Convolutional (Conv) layers, four batch normalization layers, and four Rectified Linear Units (ReLUs). The sizes of Conv layer used filters are 8, 16, 32, and 64. Four max-pooling layers are employed with a stride of 2 and a 2 × 2 window. The classification layer comprises a Fully-Connected (FC) layer and a soft-max activation function used to take the classification decision. A novel saliency-based region detection algorithm and an active contour segmentation strategy are applied to segment COVID-19 and pneumonia CT images. The acquired findings substantiate the efficacy of the proposed framework for helping the specialists in automated diagnosis applications. © 2021 Tech Science Press. All rights reserved.

Implementing oncology virtual clinics (VC) in response to COVID-19 pandemic: A transformation driven by a crisis

Background: In response to COVID-19 pandemic, we launched VC to minimize hospital visits, decrease exposures to infection and ensure continuity of care to all cancer patients. Our project aimed to assess the value of VC in management of oncology patients and the level of patient and staff satisfaction with it. Methods: On March 18, 2020, we introduced VC to all specialties at the Oncology Department, King Abdulaziz Medical City, Riyadh, Saudi Arabia. Medical records were reviewed by the oncologists to identify patients who can be evaluated through VC, those who need to come personally, and those whose appointment can be deferred. Scheduled patients in VC were contacted through locally developed application (EIADATY) or by phone call. Performing laboratory testing near home and shipping medications were done when feasible. We reviewed the data of VC from March 18 to April 30, 2020 including satisfaction results of patients and staff using Likert scale from 1 to 5 with 1 being very dissatisfied and 5 being very satisfied). Results: A total of 29 clinic sessions/week were established for different oncology services. Out of 1319 scheduled patients, 1152 (87%) answered the call (90% via phone, 5% via application and 5% used both). Of the 149 patients surveyed, their overall satisfaction ( Score>3 out of 5) with punctuality was (92%), physician interaction (90%), duration of visit (90%), medication requesting (91%), medication shipping (79%) and satisfaction with whole experience (92%). Out of 89 involved physicians, 74 (83%) completed the survey with overall satisfaction with booking process (91%), communication tools (77%), and general satisfaction (93%). 93% of physicians believed that patients were satisfied with the experience and 81 % expected to continue VC beyond the pandemic. Survey of 44 support staff (nurses, coordinators, and pharmacists) revealed similar results. Conclusions: The transition to VC was well accepted by both patients and clinicians. Optimizing the video communication tool and the process of performing pre-visit laboratory and radiology tests closer to patients home and shipping medications are essential for the enhancement of the VC function. Legal entity responsible for the study: The authors. Funding: Has not received any funding. Disclosure: N. Almutairi: Research grant/Funding (self): MSD. All other authors have declared no conflicts of interest.