Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 6 de 6
Filter
1.
Soc Netw Anal Min ; 12(1): 68, 2022.
Article in English | MEDLINE | ID: covidwho-1906563

ABSTRACT

The spread of Fake News during this global pandemic COVID-19 has dangerous consequences on economy and health of public. From origin of virus, spread, self-medication to hoaxes on vaccination, it created more panic than the fatality of the virus. For better infodemic preparedness and control, it is necessary to mitigate fear among people, manage rumours, and dispel misinformation. A survey on Fake News during COVID-19 was made by Poynter Fact Check institute. It stated that major chunk of the fake news on COVID-19 originated majorly in Brazil, India, Spain, and the United States. Fake news menace is severe in countries where the trust on online media is high such as Brazil, Kenya and South Africa. Based on these observations, this study provides preliminary insight on the co-relation of the spatial and temporal meta-information of the news like the news source country, the name of the countries specified in the news, and date of publish of news to the credibility of news. The main contribution of this study is to analyse the impact of spatial and temporal information features for classification of fake news, which to the best of our knowledge has not been explored yet. Also, these features are directly not available in any news article available online. Hence, these features are handcrafted. Meta-data of the news article such as origin of news is considered. Additional spatial information is extracted from the news article using NER tagging. Temporal information such as date of origin of news is given as an input to the LSTM model. These features are given as an input to Long Short-Term Memory (LSTM) model along with GloVe vectors and word length vector. A comparative analysis for accuracy is tested of the models with and without spatial and temporal information. The model with spatial and temporal information has achieved noteworthy results in fake news detection. To ensure the quality of prediction, various model parameters have been tuned and recorded for the best results possible. In addition to accuracy, the spatial and temporal information for fake news detection offers several other important implications for government and policy makers that will be instrumental in simulating future research on this subject.

2.
American Journal of Respiratory and Critical Care Medicine ; 205:2, 2022.
Article in English | English Web of Science | ID: covidwho-1880733
3.
12th International Conference on ICT Convergence (ICTC) - Beyond the Pandemic Era with ICT Convergence Innovation ; : 20-24, 2021.
Article in English | Web of Science | ID: covidwho-1853457

ABSTRACT

The coronavirus disease (COVID-19) highlighted our daily lives recently and caused panic over the world. In parallel, artificial intelligence contributes to presenting solutions to cease the spread of the virus by offering robust deep learning models for disease detection in chest X-ray images, despite the limited data available and the quality of its distribution as we face the problem of imbalanced data often in this kind of classification. To manage this issue, many techniques were presented recently that aim to make the distribution of the dataset homogeneous, increase the accuracy of the CNN models and obtain a correct classification. This work suggests a study of different techniques of handling the imbalanced data for the chest X-ray image classification when using distinct pre-trained CNN models. The results were unrelated depending on the approach used and the trained model.

5.
12th International Conference on Information and Communication Technology Convergence, ICTC 2021 ; 2021-October:20-24, 2021.
Article in English | Scopus | ID: covidwho-1642551

ABSTRACT

The coronavirus disease (COVID-19) highlighted our daily lives recently and caused panic over the world. In parallel, artificial intelligence contributes to presenting solutions to cease the spread of the virus by offering robust deep learning models for disease detection in chest X-ray images, despite the limited data available and the quality of its distribution as we face the problem of imbalanced data often in this kind of classification. To manage this issue, many techniques were presented recently that aim to make the distribution of the dataset homogeneous, increase the accuracy of the CNN models and obtain a correct classification. This work suggests a study of different techniques of handling the imbalanced data for the chest X-ray image classification when using distinct pre-trained CNN models. The results were unrelated depending on the approach used and the trained model. © 2021 IEEE.

6.
Circulation ; 144(SUPPL 1), 2021.
Article in English | EMBASE | ID: covidwho-1630168

ABSTRACT

Introduction: Corona Virus Disease 2019 (COVID-19) Infection is associated with acute cardiac injury. We examined the risk of in-hospital mortality in patients with concomitant COVID-19 infection and acute myocardial infarction (AMI) as compared to patients with AMI without COVID-19 infection. Hypothesis: COVID-19 is associated with increased in-hospital mortality in patients hospitalized for AMI. Methods: We conducted a systematic review and meta-analysis of published articles from January 2019 to May 2021. Literature search was performed on PubMed, Cochrane database, Embase, and Web of Science. We included studies done in patients with index hospitalization for AMI. Patients with positive COVID-19 Polymerase Chain Reaction were considered to have COVID-19 infection. We used random-effects model using the risk ratio (RR) and 95% confidence interval (CI). We used I squared test to assess for heterogeneity Results: After assessing 20 articles for full text screen for eligibility, four cohort studies met our inclusion criteria. There were a total of 1918 participants in both COVID and non-COVID groups, who were hospitalized for AMI between February 1, 2020 to June 30, 2020. 168 participants (8.76%) had concomitant COVID-19. Confounders were adjusted in only one article. Most of the confounders like age, sex, race and BMI were similar in both groups but co-morbidities were higher in COVID group in all four studies. 42 patients (61%) with COVID-19 and 69 patients (0.96%) with no COVID-19 died in hospital. Pooled data from the four studies showed patients with AMI and COVID-19 infection had more than six times increased risk of in-hospital mortality compared with patients who had AMI but no COVID-19 infection (RR 6.17, 95% CI: 4.11-9.26;I2=9%, P<0.00001). Conclusions: Our study shows that COVID-19 infection is associated with increased in-hospital mortality in patients hospitalized for AMI. Our limitations include higher comorbidities in COVID group, unable to capture all COVID patients, and high risk of bias with cohort studies. Whether patients with concomitant COVID-19 infection and AMI will benefit from unique management approaches should be further examined.

SELECTION OF CITATIONS
SEARCH DETAIL