ABSTRACT
In the past few years, social media and online news platforms have played an essential role in distributing news content rapidly. Consequently. verification of the authenticity of news has become a major challenge. During the COVID-19 outbreak, misinformation and fake news were major sources of confusion and insecurity among the general public. In the first quarter of the year 2020, around 800 people died due to fake news relevant to COVID-19. The major goal of this research was to discover the best learning model for achieving high accuracy and performance. A novel case study of the Fake News Classification using ELECTRA model, which achieved 85.11% accuracy score, is thus reported in this manuscript. In addition to that, a new novel dataset called COVAX-Reality containing COVID-19 vaccinerelated news has been contributed. Using the COVAX-Reality dataset, the performance of FNEC is compared to several traditional learning models i.e., Support Vector Machine (SVM), Naive Bayes (NB), Passive Aggressive Classifier (PAC), Long Short-Term Memory (LSTM), Bi-directional LSTM (Bi-LSTM) and Bi-directional Encoder Representations from Transformers (BERT). For the evaluation of FNEC, standard metrics (Precision, Recall, Accuracy, and F1-Score) were utilized.
ABSTRACT
It has been two years since vaccination for COVID-19 was launched worldwide. In Pakistan, the vaccination started in the beginning of 2020. Since then, several side effects were reported after vaccination, including soreness of the arm, fever, chills, malaise and diarrhoea. Axillary lymphadenopathy has been found to be associated with several conditions that include autoimmune disorders, infections, malignancy and some idiopathic causes. We present a rare case of a 30-y old female with recent recovery from COVID-19, who developed ipsilateral axillary lymphadenopathy after 15 days of Sinovac vaccination. Ultrasonography was done to confirm the diagnosis and its spread towards breast and cervical region. This case report discusses some key points and recommendations regarding unilateral axillary lymphadenopathy after COVID-19 vaccination. Copyright © 2022 Faculty of Anaesthesia, Pain and Intensive Care, AFMS. All rights reserved.
ABSTRACT
Coronavirus-19 (COVID-19) created many challenges for public health agencies and healthcare services. As a virus that created immense fear of the unknown, researchers and scientists scrambled to come up with solutions to prevent the spread and rate of infection. As previously used in combating infectious diseases, contact tracing was introduced to help decrease the rapidly increasing cases. Although contact tracing is a relatively old idea, it is still a critical part of the non-pharmaceutical interventions needed to fight such an infectious virus. However, it had to be tailored to fit this new rapidly increasing virus. This paper examines the disparities, insufficient infrastructure, and lack of proper testing and reporting during the pandemic, all of which are systemic failures of public health. These systemic failures have an impact on the effectiveness of contact tracing. All barriers will be presented with potential solutions for not only this pandemic, but for any future situations as well.
ABSTRACT
Background: We conducted a retrospective cohort study on COVID-19 patients with and without dementia by extracting data from the HCA Healthcare Enterprise Data Warehouse between January-September 2020. Aims: To describe the role of patients' baseline characteristics specifically dementia in determining overall health outcomes in COVID-19 patients. Methods: We grouped in-patients who had ICD-10 codes for dementia (DM) with age and gender-matched (1:2) patients without dementia (ND). Our primary outcome variables were in-hospital mortality, length of stay, Intensive Care Unit (ICU) admission, ICU-free days, mechanical ventilation (MV) use, MV-free days and 90-day re-admission. Results: Matching provided similar age and sex in DM and ND groups. BMI (median, 25.8 vs. 27.6) and proportion of patients who had smoked (23.3 vs. 31.3%) were lower in DM than in ND patients. The median (IQR) Elixhauser Comorbidity Index was higher in dementia patients 7 (5-10) vs. 5 (3-7, p < 0.01). Higher mortality was observed in DM group (30.8%) vs. ND group (26.4%, p < 0.01) as an unadjusted univariate analysis. The 90-day readmission was not different (32.1 vs. 31.8%, p = 0.8). In logistic regression analysis, the odds of dying were not different between patients in DM and ND groups (OR = 1.0; 95% CI 0.86-1.17), but the odds of ICU admissions were significantly lower for dementia patients (OR = 0.58, 95% CI 0.51-0.66). Conclusions: Our data showed that COVID-19 patients with dementia did not fare substantially worse, but in fact, fared better when certain metrics were considered.
ABSTRACT
The COVID-19 pandemic has made a severe impact on education system. The face to face lectures attending has replaced with online learning. These closures affected the examination system as well. Answering mechanisms have become less descriptive to adapt newer modes of evaluation thus an automated system for evaluation of descriptive answers is required. This research paper introduces a mechanism for automated scoring/grading the descriptive answers for the students. It applies efficient Natural Language Processing (NLP) and Machine Learning (ML) techniques to provide a helping hand to teachers in educational sector. Three different supervised ML models are used;Support Vector Machine (SVM), Random Forest (RF) and multinomial Naïve Bayes (NB). With these, Soft Cosine similarity is being used for analyzing similarity between datasets (dataset-1 and dataset-2) and gold standard corpus. After analyzing, it is observed that Multinomial NB model outperforms on dataset-2 with 92% accuracy. © 2021 IEEE.
ABSTRACT
Background: COVID-19 pandemic had an unprecedented impact on the delivery of patient care. Rheumatology services had to rapidly adapt to virtual consultations at the onset of the pandemic. However, providing a high quality and effective service in a virtual setting can be challenging and therefore its prudent to do a formal review and gain patient feedback to ensure that these clinics are fit for purpose. Objectives: To evaluate the impact of first wave of COVID-19 pandemic on patients with autoimmune rheumatic conditions, assess delivery of rheumatology outpatient care and record patient feedback. Methods: This study included patients on the Rheumatology clinic lists between 3rd and 31st August 2020. An electronic survey questionnaire was developed and the survey link was sent to patients via a text message using secure IT platform. Data was collected on patient demographics, diagnosis, comorbidities, treatments, clinical/ laboratory confirmed COVID-19 diagnosis, treatment interruption, impact on work, personal protective measures taken and views on virtual consultations. Results: 307 patients responded with 287 complete responses. 73.1%(223) were female and 32.4% (99) were ≥65 years of age. Rheumatoid arthritis was the most common diagnosis 41.6%(127). Hypertension was the commonest comorbidity 21.4%(64) followed by Chronic lung disease 17.3%(52). 28.8%(85) were on Hydroxychloroquine, 26.7%(79) Methotrexate, 14.2%(42) Sulfasalazine and 13.2%(39) on Prednisolone. 22.3%(66) were on Biologics: Anti TNF 12.8%(38), Tocilizumab 3.7%(11) and Rituximab 3%(9). 52.6%(161) shielded, 16.9%(55) self-isolated and 30.3%(93) only maintained social distance. 197 patients self reported as being vulnerable but based on their treatment,only 167 patiemts met the clinically extremely vulnerable (CEV) criteria and all of those received government shielding letter. 3.6%(11) had lab confirmed COVID-19, 3.2%(10) had clinically suspected COVID-19 infection. 14.3% (43) had their treatment interrupted. 4.6%(14) were unable to work from home or maintain social distancing at work. 59.8%(182) had face-to-face consultation changed to virtual. 63.2%(189) were satisfied, 28%(84) neutral and 8.7%(26) reported dissatisfaction with their consultation. 50.5%(153) were happy to continue with virtual consultation but with an option of face to face only if necessary.For consultations post COVID-19, 59.4%(182) preferred a mixture of face to face and virtual appointments. Conclusion: Majority of our patients seem happy with virtual consultations as long as they are assured of a face-to-face consultation if needed. A minority(8.7%) however, were dissatisfied. Some of the suggestions were, use of video consultations and improvement in communication before the virtual appointments. Our survey also shows that our patients have adapted well to virtual consultations and many are keen to have virtual consultation in the longer term. In our survey, only 6.8%(21) patients reported definite or clinically suspected COVID-19. Possible explanations for this include strict compliance with government advice on social distancing/shielding and limited testing at the onset of the pandemic. More patients assumed themselves to be clinically CEV than those who were actually CEV based on their treatment which is not surprising because of high level of anxiety among patients due to rapidly spreading pandemic and multiple sources of information. This feedback provides useful data which will help us to plan the delivery of rheumatology services post COVID-19 pandemic. While face-to-face patient contact is needed for comprehensive disease assessment, teaching and training, a model for the future is likely to include a combination of face-to-face and virtual consultations. This could allow a greater capacity to see new patients and reduce waiting lists. Patients with uncomplicated and stable disease could be followed up in virtual clinics. There is also a need to formally incorportate the virtual consultations into the curriculum for Rheumatology trainees.