Computer-aided COVID-19 diagnosis: a possibility?

Coronavirus Disease 2019 (COVID-19) is extremely contagious with a very high mortality rate. Effective and early diagnosis of COVID-19 is therefore crucial when treating patients and limiting its spread. The currently available methods for reliably identifying COVID are time-consuming. Infected people display various symptoms, some of which can be manifested by radiographic imaging such as chest X-rays and CT scans. Recently, many advanced machine learning and deep learning models have been proposed for predicting COVID using chest X-rays and CT scans that have paved the way for computer-aided COVID-19 diagnosis (CACD) systems. Unfortunately, most of these studies employ specific model(s) using a specific dataset making comparison difficult and inconclusive. We still lack a clear picture on which technique is best for a reliable CACD system. In this study, we provide a comprehensive analysis to determine if a CACD system can be developed that can reliably and automatically predict COVID-19 with zero human intervention using currently available tools and techniques? For this purpose, we explore and implement five machine learning models (SVM, LR, RF, KNN and ANN) and three pre-trained deep learning classifiers (VGG-16, Xception and ResNet-50) to compare their performance using 17 benchmark chest X-rays and CT-scans datasets to predict normal and infected samples. Using different classifiers and different datasets, we show that VGG16 with a superior average accuracy (99.10%) is the most suited classifier for CACD when chest X-rays are used. For CT scans, RF can also be used in addition to VGG16 as both records an average accuracy of 93% overall CT scan datasets. Based on the number of experiments, and an average accuracy of 99.10% for the chest X-rays datasets, we conclude that a reliable CACD system is possible. © 2023 Informa UK Limited, trading as Taylor & Francis Group.

Recurrence of COVID-19 Infection in Healthcare Workers after complete Vaccination

Background: COVID-19 is a novel infection. Since its first case report in 2019, it has affected population globally. Healthcare workers are at most risk as they are in direct contact with patients. Aim(s): To record recurrence of symptomatic COVID 19 after complete doses of Sinopharm vaccine among healthcare workers. Study design: Descriptive case series Place and duration of study: Department of Gastroenterology, Holy Family Hospital, Rawalpindi from 12th December 2021 to 11th June 2022. Methodology: Twenty four healthcare workers and between 20-60 years who had COVID-19 infection previously and despite receiving two doses of Sinopharm vaccine, again developed symptomatic COVID-19 diseases were enrolled. The severity was graded as per guidelines provided by CEAG. The extent of exposure during work was documented. Result(s): No significant association was found with any of the healthcare workers with duration and extent of vaccination. Upto 66% of the front line workers got COVID at 5th month and no considerable variation was noticed in other months of the vaccination. Similarly, three PGs also got COVID at 5th month and at 5th month highest number of frontline workers got COVID-19. Conclusion(s): COVID-19 reinfection can occur even after vaccination though symptoms remain relatively mild and Sinopharm provides protection against severe infection for prevention of COVID-19. Copyright © 2022 Lahore Medical And Dental College. All rights reserved.

Plotting the Literature on Precautionary Measures of COVID-19: A Scientometric Analysis of Web of Science

This study attempted to evaluate the scholarly publications on COVID-19, social distance, physical distance, social isolation, and self-isolation employing the scientometric analysis technique from 2020 to 2021. The main purpose was to consolidate the published scholarship on the COVID-19 in the Web of Science indexed documents. A total of 635 publications were found. The results indicated that social distance and COVID-19 was the top topic along with the article as a type of document, and the majority were published in the English language in 2021. The name of Gimenez-Llort L was at top of the list of authors, along with Univ. British Columbia, Canada organization, United States top country, COVID-19 as to keyword of the published documents and the main source of publication was PLOS One. Further, we had constructed figures and tables to show the trend of data. © 2021. All Rights Reserved.

Research Visualization of Different Treatment Modalities to Treat COVID-19 Infection: Bibliometric Analysis of PubMed Database

This paper designed to examine research published in PubMed indexed journals of different treatment modalities to treat COVID -19 infection employing bibliometric analysis technique from 2020 to 2021. The purpose was to consolidate the published scholarly work in the PubMed database on different treatment modalities including vaccine, oxygen supplementation, dexamethasone or steroids, aspirin, heparin, remdesivir, zinc, vitamin c or ascorbic acid, oxygen, anti-malarial like chloroquine and hydroxychloroquine, and azithromycin or macrolides. We employed a bibliometric analysis technique and found a total of 3043 published documents. The study findings depicted that vaccine and COVID-19 top was at the top of the list of topics of the published documents along with the United States as a top productive country. The name of Mahase E secured the first position in top authors, Univ. Maryland as a top organization, COVID-19 as a top keyword, COVID as top term analysis by title, and ‘BMJ (Clinical Research Ed.)‘ was the top of the published documents. © 2021. All Rights Reserved.

Trend of Research Visualization of COVID-19 Complications in PubMed Database Using Scientometric Analysis from 2020 to March 20, 2021

This study focused to evaluate the published articles on PubMed whose focus was to study the different relations between COVID 19, and different complications caused due to it. The main complications that were used to formulate this study are Deep Venous Thrombosis (DVT), Stroke, Pulmonary Embolism, Disseminated Intravascular Coagulation (DIC), Myocardial Infarction (MI), anosmia, and pneumonia. The data was extracted from the PubMed database on March 20, 2021at 03:20 PM, PST with the period of 2020 to March 20, 2021. We used Biblioshiny, VOSviewer, and MS Excel software to analyze data and found 2375 published documents. The results revealed that Pneumonia and COVID-19 was the top topic out of 2375 published documents, journal articles as the top type, and the top year was 2020. Similarly, study findings also asserted that Guaraldi, Giovanni was the top author, China was a top country, COVID-19 top keyword, and Stroke was the top source of published documents. Further, the results were illustrated in tables and figures to show the trend of the published document. © 2021. All Rights Reserved.

Spectrum of chest CT manifestations of coronavirus disease (COVID-19): A pictorial essay.

Coronavirus disease (COVID-19) is an infectious disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), which is an enveloped single-stranded RNA virus belonging to the family of betacoronaviruses. Chest computed tomography (CT) has helped us in understanding this new disease. Typical CT features of COVID-19 pneumonia are ground-glass opacities (GGO), crazy paving pattern and GGO with superimposed consolidation with a basal, posterior and peripheral lung predilection. Less commonly bronchial wall thickening, bronchial dilatation and pleural thickening are seen. Presence of pleural effusion, pericardial effusion and mediastinal lymphadenopathy is seen in severe cases. Reticulations, fibrous stripes, reverse halo sign and perilobular opacities are seen late (>2 weeks) in the course of illness. We aim to present a pictorial review of CT imaging findings in COVID-19 to illustrate the typical and atypical manifestations of this disease in a bid to familiarize radiologists with the myriad imaging manifestations of this disease.

Volume and Acuity of Emergency Department Visits Prior To and After COVID-19.

BACKGROUND: There are scant data regarding the change in volume and acuity of patients presenting to emergency departments (EDs) after Coronavirus Disease 2019 (COVID-19), compared with the pre-COVID-19 era. OBJECTIVE: To determine ED volumes and triage acuity prior to and after COVID-19. METHODS: We determined the volume of patients presenting to four large EDs affiliated with general, cardiac, cancer, and obstetrics hospitals, and the acuity of presenting illness (using the Canadian Triage Acuity Scale [CTAS]) for March and April 2020 and compared them with the same months in 2019 and January 2020. Together, these facilities see over 80% of the ED visits in Qatar. The first COVID-19 patient in Qatar was diagnosed on February 29, 2020. RESULTS: A total of 192,157 ED visits were recorded during the study period. There was a 20-43% overall drop in number of ED visits, with significant variability across hospitals. The Heart Hospital experienced the sharpest decline (33-89%), and the National Center for Cancer Care and Research experienced the least decline in volumes. The decline was observed across all CTAS levels, with the largest decline observed in individuals presenting with CTAS 1 and 2 (26-69% decline month by month). No increase in overall number of deaths or crude mortality rate was observed in the COVID-19 era, according to national statistics. CONCLUSIONS: Sharp declines in ED visits and the triage acuity seen in both general and specialty hospitals raise the concern that severely ill patients may not be seeking timely care, and a surge may be expected once current restrictions on movement are lifted.

Hospital Admission Rates, Length of Stay and In-hospital Mortality for Common Acute Care Conditions in COVID-19 vs. Pre-COVID-19 Era (preprint)

BackgroundImpact of COVID-19 upon acute care admission rates and patterns are unknown. We sought to determine the change in rates and types of admissions to tertiary and specialty care hospitals in the COVID-19 era compared with pre-COVID-19 era. MethodsAcute care admissions to the largest tertiary care referral hospital, designated national referral centers for cardiac, cancer and maternity hospital in the State of Qatar during March 2020 (COVID-19 era) and January 2020 and March 2019 (pre-COVID-19 era) were compared. We calculated total admissions, and admissions for eight specific acute care conditions, in-hospital mortality rate and length of stay at each hospital. ResultsA total of 18,889 hospital admissions were recorded. A sharp decline ranging from 9%-75% was observed in overall admissions. A decline in both elective and non-elective surgeries was observed. A decline of 9%-58% was observed in admissions for acute appendicitis, acute coronary syndrome, stroke, bone fractures, cancer and live births, while an increase in admissions due to respiratory tract infections was observed. Overall length of stay was shorter in the COVID-19 period possibly suggesting lesser overall disease severity, with no significant change in in-hospital mortality. Unadjusted mortality rate for Qatar showed marginal increase in the COVID-19 period. ConclusionsWe observed a sharp decline in acute care hospital admissions, with a significant decline in admissions due to seven out of eight acute care conditions. This decline was associated with a shorter length of stay, but not associated with a change in in-hospital mortality rate.