A COVID-19 Infection Prediction Model in Egypt Based on Deep Learning Using Population Mobility Reports

The rapidly spreading COVID-19 disease had already infected more than 190 countries. As a result of this scenario, nations everywhere monitored confirmed cases of infection, cures, and fatalities and made predictions about what the future would hold. In the event of a pandemic, governments had set limit rules for the spread of the virus and save lives. Multiple computer methods existed for forecasting epidemic time series. Deep learning was one of the most promising methods for time-series prediction. In this research, we propose a model for predicting the spread of COVID-19 in Egypt based on deep learning sequence-to-sequence regression, which makes use of data on the population mobility reports. The presented model utilized a new combined dataset from two different sources. The first source is Google population mobility reports, and the second source is the number of infected cases reported daily "world in data” website. The suggested model could predict new cases of COVID-19 infection within 3–7 days with the least amount of prediction error. The proposed model achieved 96.69% accuracy for 3 days of prediction. This study is noteworthy since it is one of the first trials to estimate the daily influx of new COVID-19 infections using population mobility data instead of daily infection rates. © 2023, The Author(s).

SARS COV-2 and other viral etiology as a possible clue for the olfactory dilemma

Background: Post-viral anosmia is responsible for more than 40% of cases of anosmia. Anosmia has been a neglected symptom in the primary healthcare setting until the emergence of the SARS-CoV-2 pandemic. The spread of SARS-CoV-2 infection highlighted new atypical symptoms of the disease, including anosmia, which has become one of the diagnostic symptoms of the disease, and epidemiological concern. We aimed to detect the incidence of SARS-CoV-2 infection within patients presented with anosmia and to test for other respiratory viruses in the negative COVID-19 patients. We also detected the recovery of anosmia and IgM/IgG against COVID-19. We prospectively included 60 outpatients with the major complaint of anosmia. Nasopharyngeal swabs were done for SARS-CoV-2 real-time PCR, and if negative, PCR to other respiratory pathogens was tested. After one month, we inquired about the recovery of smell loss together with testing for antibodies against SARS-CoV-2. Result(s): Sixty patients were enrolled in the study. Forty-six patients (76.7%) were SARS-CoV-2 PCR positive and 14 (23.3%) were negative. Rhinovirus was the commonest isolated pathogen in the negative cases (5/14). Complete recovery of anosmia occurred in 34 patients (56.7%), while partial recovery in 24 (40.0%), and no recovery in 2 patients (3.3%). The median time to complete recovery was 10 days. 28.3% (13/46) of the patients showed negative antibody response for both IgG and IgM. Conclusion(s): Sudden-onset anosmia is a symptom that is highly predictive of being COVID-19-infected. While recovery is expected within 2 weeks, some patients have no antibodies against SARS-CoV-2.Copyright © 2022, The Author(s).

Comprehensive evaluation of otorhinolaryngological symptoms in COVID-19 patients

Introduction: The aim of this study is to comprehensively evaluate the incidence and natural course of otorhinolaryngological symptoms of COVID-19 infection and its relations to each other and patient's demographics. Method(s): This is a prospective study conducted on symptomatic adult patients proven to be infected with COVID-19. Detailed history was taken from each patient including onset of symptoms. Symptoms were followed up tightly. We focus on otorhinolaryngological (ORL) symptoms and their duration and onset in relation to other symptoms. Data were collected and analyzed in detail. Result(s): Six-hundred eighty-six patients were included in the study, their age ranged from 19-75 years old, and of them 55.1% were males. Cough was found in 53.1% of cases followed by sore throat in 45.8%, anosmia/ hyposmia in 42.3%, headache in 42%, rhinorrhea in 19.5%, dry mouth in 7.6%, globus in 6.1%, epistaxis in 4.4%, and hearing loss in 0.6%. In non-ORL symptoms, fever was found in 54.2%, malaise in 55.1%, dyspnea in 49.3%, and diarrhea in 27.2%. The first symptom was anosmia in 15.7% of cases, sore throat in 6.1 %, cough in 7.9%, and headache in 13.4% of cases. Fever was the first symptom in 22.7%, malaise in 25.1%, and diarrhea in 6.4%. Headache occurred for 5.5 +/- 2 days, anosmia/hyposmia 3 to > 30 days, sore throat 4.1 +/- 1.2 days, rhinorrhea 4.3 +/- 1.1, cough 7.4 +/- 2.5 days, fever 4.7 +/- 2 days, and malaise 6.5 +/- 2.4 days. The cluster of COVID-19-related symptoms showed nine principal components. Conclusion(s): Otorhinolaryngological symptoms are main symptoms in COVID-19 infection, and they should be frequently evaluated to detect suspected cases especially in pauci-symptomatic patients and to properly manage infected patients.Copyright © 2022, The Author(s).

Cluster analysis of biochemical markers as predictor of COVID-19 severity

Numerous blood biomarkers are altered in COVID-19 patients;however, no early biochemical markers are currently being used in clinical practice to predict COVID-19 severity. COVID-19, the most recent pandemic, is caused by the SRS-CoV-2 coronavirus. The study was aimed to identify patient groups with a high and low risk of developing COVID-19 using a cluster analysis of several biomarkers. 137 women with confirmed SARS CoV-2 RNA testing were collected and analyzed for biochemical profiles. Two-dimensional automated hierarchy clustering of all biomarkers was applied, and patients were sorted into classes. Biochemistry marker variations (Ferritin, lactate dehydrogenase LDH, D-dimer, and C- reactive protein CRP) have split COVID-19 patients into two groups(severe cases and non-severe cases groups). Ferritin, lactate dehydrogenase LDH, D-dimer and CRP were markedly increased in COVID-19 patients in the first group (severe cases). Our findings imply that early measured levels of (Ferritin, lactate dehydrogenase LDH, D-dimer, and C- reactive protein CRP) are linked to a decreased probability of COVID-19 severity. Elevated levels of this biomarker may predict COVID severity development.

Cluster Analysis of Biochemical Markers as Predictor of COVID-19 Severity

Numerous blood biomarkers are altered in COVID-19 patients;however, no early biochemical markers are currently being used in clinical practice to predict COVID-19 severity. COVID-19, the most recent pandemic, is caused by the SRS-CoV-2 coronavirus. The study was aimed to identify patient groups with a high and low risk of developing COVID-19 using a cluster analysis of several biomarkers. 137 women with confirmed SARS CoV-2 RNA testing were collected and analyzed for biochemical profiles. Two-dimensional automated hierarchy clustering of all biomarkers was applied, and patients were sorted into classes. Biochemistry marker variations (Ferritin, lactate dehydrogenase LDH, D-dimer, and C- reactive protein CRP) have split COVID-19 patients into two groups(severe cases and non-severe cases groups). Ferritin, lactate dehydrogenase LDH, D-dimer and CRP were markedly increased in COVID-19 patients in the first group (severe cases). Our findings imply that early measured levels of (Ferritin, lactate dehydrogenase LDH, D-dimer, and C- reactive protein CRP) are linked to a decreased probability of COVID-19 severity. Elevated levels of this biomarker may predict COVID severity development. © 2022 University of Baghdad. All rights reserved.

The impact of COVID-19 on blood coagulation profile among Sudanese hospitalized adult patients

Covid-19 is a severe acute respiratory syndrome, the disease presents with a ranging from asymptomatic to severe symptomatic illness with multiple organ failure and death, and can cause a severe effect on the coagulation system. This study aimed to determine the effect of the covid 19 on the extrinsic and intrinsic pathway of coagulation [prothrombin time(PT), international normalized ratio (INR), and activated partial thromboplastin time (APTT)] and to determine the association of age and gender with the severity of COVID-19 in Sudan in order to improve the outcome. A cross-sectional study carried out among 487 COVID-19 patients attending Khartoum State. COVID-19 patients were confirmed by RT-PCR. For all patients, the prothrombin times (PT), International normalized ratio (INR), and Activated partial thromboplastin (APTT) were estimated by using a semi-automated coagulometer analyzer. Patients were divided into three subclass groups according to the Severity of COVID-19 (mild, severe in the emergency room) (ER) and intensive care unit (ICU), and the clotting factors values were compared between the groups. The results were statically analyzed by spss version 21 for data analysis. These results showed statistically significant increased Levels of PT, INR, and APTT for all (P. value = 0.000), compared to the control group. Also, the levels of coagulation tests were higher in ICU COVID-19 patients (P. value = 0.000) compared to mild and severe subgroups. This study concluded that: coagulation clotting times were increased in COVID-19 patients, especially among patients in ICU which could be a marker for DIC and even death.

Detection of Coronavirus (COVID-19) Associated Pneumonia Based on Generative Adversarial Networks and a Fine-Tuned Deep Transfer Learning Model Using Chest X-ray Dataset

The COVID-19 coronavirus is one of the devastating viruses according to the world health organization. This novel virus leads to pneumonia, which is an infection that inflames the lungs’ air sacs of a human. One of the methods to detect those inflames is by using x-rays for the chest. In this paper, a pneumonia chest x-ray detection based on generative adversarial networks (GAN) with a fine-tuned deep transfer learning for a limited dataset will be presented. The use of GAN positively affects the proposed model robustness and made it immune to the overfitting problem and helps in generating more images from the dataset. The dataset used in this research consists of 5863 X-ray images with two categories: Normal and Pneumonia. This research uses only 10% of the dataset for training data and generates 90% of images using GAN to prove the efficiency of the proposed model. Through the paper, AlexNet, GoogLeNet, Squeeznet, and Resnet18 are selected as deep transfer learning models to detect the pneumonia from chest x-rays. Those models are selected based on their small number of layers on their architectures, which will reflect in reducing the complexity of the models and the consumed memory and time. Using a combination of GAN and deep transfer models proved it is efficiency according to testing accuracy measurement. The research concludes that the Resnet18 is the most appropriate deep transfer model according to testing accuracy measurement and achieved 99% with the other performance metrics such as precision, recall, and F1 score while using GAN as an image augmenter. Finally, a comparison result was carried out at the end of the research with related work which used the same dataset except that this research used only 10% of original dataset. The presented work achieved a superior result than the related work in terms of testing accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Sensitivity of Chest Computed Tomography Scan in Diagnosis of SARS-CoV-2: A Meta-analysis Study

Background: Early diagnosis of Coronavirus disease 2019 (COVID-19) is crucial for disease treatment and control. Compared to Real-time Reverse-transcription polymerase chain reaction (rRT-PCR), chest computed tomography (CT) scan imaging may be a more practical and rapid method to diagnose and assess COVID-19, especially in the pandemic. Aim: To conduct a meta-analysis study regarding the sensitivity of chest CT scan in detecting Coronavirus Disease 2019 (COVID-19). Patients and Methods: Using MEDLINE database (https://pubmed.ncbi.nlm.nih.gov/), Google Scholar and Scopus, we conducted a systematic search to identify relevant studies published within the last 6 months (from November 2019 till 20th of April 2020), appropriate articles were accessed in full text to determine eligibility and extract data by two reviewers. Results: Fifteen retrospective studies were included, and their results were pooled in this meta-analysis. Chest CT scan showed positive finding in 2714 out of 3130 scanned patients. Sensitivity of the chest CT scan for diagnosis of COVID-19 could be extracted from all studies ranging from 0.61-0.99. There was considerable heterogeneity across studies. There was no evidence of publication bias. Conclusion: Chest CT scan can provide a speedy and effective method to early recognize suspicious COVID-19 cases, contributing to reduction of cross infection due to its great sensitivity. But we should be cautious during interpreting these results since established available information about COVID-19 are rapidly evolving all over the world, in addition, most of the published information are incomplete. © 2021, Egyptian Society of Ear Nose Throat and Allied Sciences. All rights reserved.

Spike antibody seroconversion and breadth following SARS-CoV-2 vaccination in Australian people with multiple sclerosis

Background: COVID-19 vaccination induces protective Spike antibodies. Some responses are attenuated in people with multiple sclerosis (MS) on high efficacy disease-modifying therapies (DMT).Whether antibodies afford immunity against emerging SARS-CoV-2 Variants of Concern (VoC) such as Delta and Omicron is unknown. Aim(s): To assess the longevity and breadth of Spike antibody in MS patients after COVID-19 vaccination. Objective(s): To determine seroconversion and antibody binding toVoC Spike. Method(s): Spike antibodies to Clade A SARS-CoV-2 were assessed in 535 MS sera at baseline (n=292), 1 (n=141) and 6 month (n=67) post-second dose, and 1 month post-third dose (n=35), and 489 health worker controls. When known, COVID- 19 vaccines were BNT162b2 (n= 489 controls, n=108 MS patients) and ChAdOx1-S (n=37).Spike antibody binding to VoC Delta and Omicron BA1 was assessed in 68 sera 1 month post-second dose. Demographic and DMT information was available in 269 patients. Result(s): 123/141 sera at 1 month post-second dose, 66/67 at 6 months post-second dose, and 26/35 at 1 month post-third dose were positive for Spike antibodies.Patients who did not seroconvert at 1 and 6 month post-second and 1 month post-third dose (n=28) were treated with ocrelizumab (n=22), cladribine (n=1), fingolimod (n=4), and siponimod (n=1). At 1 month post-second dose, the median and IQR Spike antibody levels were 67,224+/- 101,251 in the seroconverted MS group compared to 145,510+/- 99,669 in controls (n=489). When patient sera were assessed for binding to Clade A Spike, and VoC Delta and Omicron BA1 Spikes, most sera were able to bind the three different Spike antigens (n=61). However, Spike antibody immunoreactivity was decreased by 70% against Delta Spike and 90% for Omicron BA1 Spike compared to the original clade A Spike.As observed for Clade A Spike antibody, DMTs, such as ocrelizumab, fingolimod, and ofatumumab, decreased the antibody binding to Delta and Omicron Spike. Still, the pattern of antibody recognition was similar between the three Spikes and all DMTs analysed, i.e. alemtuzumab, natalizumab, teriflunomide, and interferons. Our data suggest that, irrespectively of DMTs, antibodies generated after vaccination did not bind Spike from recent VoCs to the same extent as the original Spike used in COVID-19 vaccines. Conclusion(s): Some DMTs reduce Spike antibody titres or prevent seroconversion. The sequence of Spike used in the first generation of vaccines may need to be updated for emerging VoC.

Successful Story of Conversion of Cinacalcet to Etelcalcetide During the COVID-19 Pandemic

Background: Hamad general Hospital is the main provider of (HD) in Qatar with 932 patients. We established a team from dialysis nurses under direct nephrologist supervision for management of (MBD). We introduced Etelcalcetide in Qatar in May 2021 for HD patients unable to tolerate oral cinacalcet (GIT symptoms) especially during the COVID-19 pandemic where patients had difficulties dispensing medicine and have proper follow up Methods: Our study followed patients from May 2021 till March 2022. We included HD for >6 months patients with (HPT) despite being on cinacalcet therapy. Patients recruited from all HD centers (4) in Qatar. Data collected through electronic medical records. Result(s): 50 patients fulfilled inclusion criteria and were included in study period. Median (PTH) on cinacalcet was 946 pg./ml (Mean 1123pg/ml). After conversion to Etelcalcetide, PTH median level had significant improvement to 623 pg./ml (mean 749 pg./ ml). Average improvement in PTH level was 46% (36% of patients with 50% improvement and 48% of patients with >50% improvement). The Median dose for Etelcalcetide was 21.5mg /week. (Patients with within our PTH target range (150-500pg/ml) improved from 8% in May 2021 (on cinacalcet) to 38% in March 2022 (on Etelcalcetide) p=0.0003) while patients with PTH above 800 decreased from 50% to 20% for the same period (p=0.001). Reasons for conversion from Cinacalcet to Etelcalcetide were noncompliance due to GIT side effects (with resistant elevation of PTH despite optimal dose (90% of patients) also due to the COVID-19 pandemic and its effect in following medication in the face of shortage of our nurses and physician. Conclusion(s): Our project to optimize MBD management in HD patients with uncontrolled HPT not tolerating Cinacalcet by utilizing Etelcalcetide showed significant improvement in PTH outcomes. It was well tolerated with no reported significant side effects. Utilizing MBD team proven to be a wise decision during the peak of the COVID-19 pandemic with physician shortage and service disturbances. (Figure Presented).

Impact of COVID-19 on endoscopic follow-up of gastroesophageal varices.

Background: Portal hypertension is considered as a major complication of liver cirrhosis. Endoscopy plays a main role in managing of gastrointestinal complications of portal hypertension. Endoscopists are at increased risk for COVID-19 infection because upper gastrointestinal (GI) endoscopy is a high-risk aerosol-generating procedure and may be a potential route for COVID-19. Objectives: To compare the outcome between cirrhotic patients who underwent classic regular endoscopic variceal ligation after primary bleeding episode every 2-4 weeks, and those presented during the era of COVID-19 and their follow-up were postponed 2 months later. Methods: This retrospective study included cross-matched 238 cirrhotic patients with portal hypertension presented with upper GI bleeding, 112 cirrhotic patients presented during the era of COVID19 (group A) underwent endoscopic variceal ligation, another session after 2 weeks and their subsequent follow-up was postponed 2 months later, and 126 cirrhotic patients as control (group B) underwent regular endoscopic variceal band ligation after primary bleeding episode every 2-4 weeks. Results: Eradication of varices was achieved in 32% of cases in group A, and 46% in group was not any statistically significant (p > 0.05); also, there was no any statistical significant difference between both groups regarding occurrence of rebleeding, post endoscopic symptoms, and mortality rate (p > 0.05). Conclusion: Band ligation and injection of esophageal and gastric vary every 2 months were as effective and safe as doing it every 2 to 4 weeks after primary bleeding episode for further studies and validation.

Automated COVID-19 misinformation checking system using encoder representation with deep learning models

Social media impacts society whether these impacts are positive or negative, or even both. It has become a key component of our lives and a vital news resource. The crisis of COVID-19 has impacted the lives of all people. The spread of misinformation causes confusion among individuals. So automated methods are vital to detect the wrong arguments to prevent misinformation spread. The COVID-19 news can be classified into two categories: false or real. This paper provides an automated misinformation checking system for the COVID-19 news. Five machine learning algorithms and deep learning models are evaluated. The proposed system uses the bidirectional encoder representations from transformers (BERT) with deep learning models. detecting fake news using BERT is a fine-tuning. BERT achieved accuracy (98.83%) as a pre-trained and a classifier on the COVID-19 dataset. Better results are obtained using BERT with deep learning models, which achieved accuracy (99.1%). The results achieved improvements in the area of fake news detection. Another contribution of the proposed system allows users to detect claims' credibility. It finds the most related real news from experts to the fake claims and answers any question about COVID-19 using the universal-sentence-encoder model. © 2023, Institute of Advanced Engineering and Science. All rights reserved.

COVID-19 Chest X-rays Classification Through the Fusion of Deep Transfer Learning and Machine Learning Methods

One of the most challenging issues that humans face in the last decade is in the health sector, and it is threatening his existence. The COVID-19 is one of those health threats as declared by the World Health Organization (WHO). This spread of COVID-19 forced WHO to declare this virus as a pandemic in 2019. In this paper, COVID-19 chest X-rays classification through the fusion of deep transfer learning and machine learning methods will be presented. The dataset “DLAI3 Hackathon Phase3 COVID-19 CXR Challenge” is used in this research for investigation. The dataset consists of three classes of X-rays images. The classes are COVID-19, Thorax Disease, and No Finding. The proposed model is made up of two main parts. The first part for feature extraction, which is accomplished using three deep transfer learning algorithms: AlexNet, VGG19, and InceptionV3. The second part is the classification using three machine learning methods: K-nearest neighbor, support vector machine, and decision trees. The results of the experiments show that the proposed model using VGG19 as a feature extractor and support vector machine. It reached the highest conceivable testing accuracy with 97.4%. Moreover, the proposed model achieves a superior testing accuracy than VGG19, InceptionV3, and other related works. The obtained results are supported by performance criteria such as precision, recall, and F1 score. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Prior Diagnosis of COVID Has No Increased Complications in Total Joint Arthroplasty.

Introduction Although a substantial portion of the United States population has been infected with and recovered from Coronavirus Disease-19 (COVID-19), many patients may have persistent symptoms and complications from disease-driven respiratory disease, arrhythmias, and venous thromboembolism (VTE). With institutions resuming elective total joint arthroplasties (TJA), it is unclear whether a prior resolved diagnosis of COVID has any implications on postoperative outcomes. Methods All elective TJA performed in 2021 at our institution were retrospectively reviewed and a history of prior COVID+ result recorded. Baseline demographics, days from prior COVID+ result to surgery date, preoperative methicillin-resistant Staphylococcus aureus (MRSA) nares colonization, and laboratory markers were obtained to determine baseline characteristics. Postoperative estimated blood loss (EBL), length of stay (LOS), rate of revision surgery, and discharge destination were compared between groups. Perioperative and postoperative rates of VTE, urinary tract infection (UTI), pneumonia, postoperative oxygen supplementation, cardiac arrhythmia, renal disease, sepsis, and periprosthetic joint infections within six months of surgery were recorded. Results Of the 155 elective TJA performed in 2021, 24 patients had a prior COVID+ diagnosis with a mean of 253 days from positive result to surgery date. There were no significant differences in baseline demographics, comorbidities, and preoperative lab markers between groups. Surgeries on patients with a prior COVID+ had a significantly higher EBL (260 vs 175cc), but postoperative outcomes of VTE, UTI, pneumonia, oxygen supplementation requirement, nares MRSA+, cardiac disease, and infection rates between groups were similar. Bivariate logistic regression revealed increased days from COVID+ diagnosis (>6 months) to surgery date were associated with a shorter LOS. Conclusion Although a prior COVID+ diagnosis had increased intraoperative blood loss, there were no significant differences in respiratory, infectious, cardiac, and thromboembolic complications up to six months after elective TJA. This study suggests that asymptomatic C+ patients receiving elective TJA do not require more aggressive prophylactic anticoagulation or antibiotic regimens to prevent VTE or perioperative infections. As institutions around the nation resume pre-COVID rates of arthroplasty surgeries, a prior diagnosis of COVID appears to have no effects on postoperative complications.

Association between Atherogenic Index and Cholesterol to HDL Ratio in COVID-19 Patients During the Initial Phase of Infection.

This case-control study aimed to assess pathologic alteration in the serum levels of the atherogenic index, cholesterol to high-density lipoprotein (HDL) ratio, HDL cholesterol, total cholesterol, triglyceride, HbA1c, and glucose in 158 COVID-19 patients who were hospitalized in Erbil international hospital, Erbil, Iraq, between January and May 2020, in the early stage of infection. The patients were confirmed for SARS-CoV-2 on admission. The laboratory test results were compared between this group and a group of healthy individuals (n=158). A statistically significant difference was found between the studied factors in healthy controls and COVID-19 patients, except for low-density lipoprotein (LDL) cholesterol (P=0.13). In the case of COVID-19 patients, total levels of cholesterol and HDL cholesterol were significantly lower than controls (P<0.003). Triglyceride, VLDL cholesterol, atherogenic index, and total cholesterol to HDL ratio were found to be significantly higher in COVID-19 patients, compared to controls (P<0.005). Atherogenic index were found to be positively correlated with triglyceride (r=0.88, P=0.00), HbA1C (r=0.6, P=0.05), and glucose index (r= 0.62, P= 0.05), and the ratio of cholesterol to HDL (r=0.64, P=0.04). In contrast, no correlation was found between atherogenic index and cholesterol to HDL ratio in controls. The results of the current study indicated that risk factors for the cardiovascular disease increased in patients with COVID-19 infection, which included atherogenic index, cholesterol to HDL ratio, as well as the association between atherogenic index, and all were organized in one cluster. Therefore, lipids can perform a vital physiological function in patients infected with COVID-19.

Within the Protection of COVID-19 Spreading: A Face Mask Detection Model Based on the Neutrosophic RGB with Deep Transfer Learning

COVID-19’s fast spread in 2020 compelled the World Health Organization (WHO) to declare COVID-19 a worldwide pandemic. According to the WHO, one of the preventative countermeasures against this type of virus is to use face masks in public places. This paper proposes a face mask detection model by extracting features based on the neutrosophic RGB with deep transfer learning. The suggested model is divided into three steps, the first step is the conversion to the neutrosophic RGB domain. This work is considered one of the first trails of applying neutrosophic RGB conversion to image domain, as it was commonly used in the conversion of grayscale images. The second step is the feature extraction using Alexnet, which has been small number of layers. The detection model is created in the third step using two traditional machine learning algorithms: decision trees classifier and Support Vector Machine (SVM). The Simulated Masked Face dataset (SMF) and the Real-World Mask Face dataset (RMF) are merged to a single dataset with two categories (a face with a mask, and a face without a mask). According to the experimental results, the SVM classifier with the True (T) neutrosophic domain achieved the highest testing accuracy with 98.37%. © 2022

A Comparative Study of Machine Learning Approaches for Rumors Detection in Covid-19 Tweets

Analysing social media content becomes a crucial task due to the tremendous usage of social media platforms. In the era of COVID-19, detecting rumors becomes a vital task. In natural language processing, detecting rumors is a challenging task due to the complexity of rumors and tracking the source of rumors. In this paper, we proposed a machine learning-based model for rumors detection in COVID-19 related tweets for both English and Arabic Languages. Different machine learning algorithms have been implemented and Term Frequency/Inverse Document Frequency tf/idf has been used for feature extraction. The performance of all implemented classifiers has been analysed and compared. Our approach does not use external resources or data and depends only on the given training data. © 2022 IEEE.

Augmentation des infections invasives à Hib chez les jeunes enfants dans un contexte de couverture vaccinale élevée en France, 2018-2021

Introduction Les infections invasives à Haemophilus influenzae (Hib) chez les jeunes enfants sont devenues très rares depuis l'introduction de la vaccination contre Hib dans le calendrier vaccinal du nourrisson en 1993. Depuis 2013, le schéma complet de vaccination repose sur 2 doses en primo-vaccination (2, 4 mois) et 1 dose de rappel (11 mois). Cette vaccination est obligatoire pour les enfants nés à partir de 2018. Cette étude vise à caractériser l'augmentation de l'incidence des infections invasives à Hib chez les jeunes enfants observée depuis 2018. Matériels et méthodes Nous avons inclus les infections invasives à Hib chez les enfants âgés de moins de 5 ans en France métropolitaine entre 2001 et 2021 confirmées par le Centre national de référence (CNR) des méningocoques et Haemophilus influenzae. Les critères de confirmation biologique étaient les suivants: isolement ou détection de Hib à partir d'un site stérile;ou épiglottite associée à l'isolement de Hib dans un prélèvement trachéal. Les données du CNR ont été complétées par les données recueillies par les pédiatres participant à l'observatoire national des méningites bactériennes de l'enfant coordonné par ACTIV-GPIP. Pour la période 2018-2021, les cas ont été décrits selon leurs caractéristiques cliniques, épidémiologiques et leur statut vaccinal pour Hib. Pour les enfants ayant reçu un schéma complet, la réponse en anticorps a été analysée par le CNR à partir de prélèvements sanguins recueillis lors de l'admission à l'hôpital, puis 3 à 8 semaines plus tard. Résultats Le nombre d'infections invasives à Hib chez les enfants âgés de moins de 5 ans a fortement augmenté au cours des dernières années, passant de moins de 6 cas par an sur la période 2011-2017 à 13 en 2018, 12 en 2019, 21 en 2020 et 44 en 2021. L'incidence a notamment augmenté chez les enfants âgés de 6-11 mois, 19-35 mois et 3-4 ans. Au cours de la période 2018-2021, la proportion de cas correctement vaccinés pour leur âge était élevée : 24/29 (72%) des enfants âgés de 6 à 11 mois, et 27/39 (69%) des enfants âgés de 12 mois et plus. Pour 11 des 14 cas pour lesquels la réponse en anticorps a été explorée au CNR, la cinétique des anticorps après l'admission suggérait une réponse anamnestique en faveur d'un échec vaccinal secondaire. Conclusion Cette analyse a mis en évidence une augmentation des infections invasives à Hib chez les jeunes enfants en 2020 et 2021. Cela contraste avec la diminution observée pour d'autres bactéries à transmission respiratoire responsables d'infections invasives en lien avec les mesures de lutte contre le COVID-19. La proportion élevée de cas correctement vaccinés pour leur âge est préoccupante. Des études complémentaires sont nécessaires pour évaluer l'immunogénicité, l'efficacité, et la durée de protection de la vaccination des nourrissons selon le schéma actuellement en vigueur. Aucun lien d'intérêt

Steganography Adaptation Model for Data Security Enhancement in Ad-Hoc Cloud Based V-BOINC Through Deep Learning

Cloud computing’s automation, scalability, and availability were vital features in the early days of digital transformation. Meanwhile, substantial concerns were expressed about cloud security and privacy. Due to the COVID-19 outbreak, several businesses have had serious issues speeding up their cloud migration efforts. This work intends to improve steganography in ad-hoc cloud systems using deep learning. This study is implemented in two phases. Phase 1: The ‘Ad-hoc Cloud System’ concept and deployment method were created using V-BOINC, a tool that allows developers to bypass application-level security checks, the implemented ad-hoc cloud system was compared Amazon AC2 and showed high evaluation rate in some matrices. Phase 2: We evaluate the data transmission security in ad-hoc cloud systems using a modified steganography with deep learning usage to replace or enhance an image-hiding system. In this study, the proposed model inputs data/images into the ad-hoc cloud system to guarantee high rate of data/image concealing. Statistically, a systematic steganography model hides lower message detection rates, the proposed deep steganography approach outperformed several attacks in the ad-hoc cloud environment. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

A meta-analysis of Nigella sativa in respiratory disorders

Plants have always been used as a remedy for various illnesses and their widespread use is because they are safe, effective, and affordable when compared to allopathic medications. Nigella sativa is considered as a miracle herb and is accepted as a panacea in Middle East and South Asian countries. Numerous therapeutic benefits of the plant extract against diabetes, hypertension, pediatric seizures, opioid dependence, anxiety, arthritis, various infectious diseases, infertility, dyspepsia, asthma, allergic rhinitis were demonstrated by clinical studies. The bronchodilating property of few constituents of the seeds contributes its potency against different illnesses of the respiratory system, including asthma, dyspnea, nasal dryness, and rhinitis. According to the World Health Organization (WHO), respiratory diseases are second to cardiovascular disease and make up to five of the 30 most common causes of deaths worldwide. Currently, there is no cure to the chronic respiratory diseases, but various forms of treatments may help to ameliorate the quality of life of people suffering with the condition. An increasing number of people are approaching toward natural remedy to improve their respiratory symptoms, this review is planned to summarize all the therapeutic benefits of N. sativa against different respiratory illnesses which were characterized by experimental and clinical studies. © 2022 Elsevier Inc. All rights reserved.