Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 5 de 5
Filter
1.
13th Asian Control Conference, ASCC 2022 ; : 465-469, 2022.
Article in English | Scopus | ID: covidwho-1994839

ABSTRACT

Coronavirus pandemic that has spread all over the world, is one of its kind in the recent past, that has mobilized researchers in areas such as (not limited to) pre-screening solutions, contact tracing, vaccine developments, and crowd estimation. Pre-screening using symptoms identification, cough classification, and contact tracing mobile applications gained significant popularity during the initial outbreak of the pandemic. Audio recordings of coughing individuals are one of the sources that can help in the pre-screening of COVID-19 patients. This research focuses on quantitative analysis of covid cough classification using audio recordings of coughing individuals. For analysis, we used three different publicly available datasets i.e., COUGHVID, NoCoCoDa, and a self-collected dataset through a web application. We observed that wet cough has more correlation with covid cough as opposed to dry cough. However, the classification model trained with wet and dry coughs, both, has similar test performance as that of the model trained with wet cough samples only. We conclude that audio-signal recordings of coughing individuals have the potential as a pre-screening test for COVID-19. © 2022 ACA.

2.
4th International Conference on Innovative Computing (ICIC) ; : 541-+, 2021.
Article in English | Web of Science | ID: covidwho-1985465

ABSTRACT

The catastrophic outbreak of SARS-CoV-2 or COVID-19 has taken the world to uncharted waters. Detecting such an outbreak at its early stages is crucial to minimize its spread but is very difficult as well. The pandemic situation is not yet under control as the virus tends to evolve and develop mutations. This further complicates the development of machine learning or AI models that can automatically detect the disease in the general public. However, researchers worldwide have been putting their incredible efforts into devising mechanisms that help analyze and control the pandemic situation. Many prediction models have been developed to predict COVID-19 infection risk that helps in mitigating the burden on the healthcare system. These models help the medical staff, especially when healthcare resources are limited. As a contribution to society's well-being, this research work deploys a machine learning prediction model that predicts COVID-19 patients with COVID-19 symptoms. Key pieces of information from RT-PCR test data results by the Israeli ministry of health publicly available have been distilled, preprocessed, and then used to train our prediction model. The model is trained on eight features, out of which five are the primary clinical symptoms of this fatal virus: cough, sore throat, fever, headache, breath shortness;and the other three features are gender, test indication, and age. Machine learning models can be considered for COVID-19 testing, especially when resources are limited. We have achieved highly accurate results in COVID-19 prediction with our prediction model. The model is best suited in urgent situations where there is a limitation of testing resources.

3.
Gastroenterology ; 160(6):S-757-S-758, 2021.
Article in English | EMBASE | ID: covidwho-1591206

ABSTRACT

Introduction: Patient with chronic liver disease (CLD) can have adverse outcomes in setting of COVID-19 infection. Our goal is to determine the prevalence of liver disease in COVID-19 infection and outcomes as compared to individuals without CLD. Methods: We conducted a retrospective review of the patients admitted for COVID-19 infection from March 1st, 2020 till May 31st, 2020. The patients who had chronic liver disease were identified based on imaging interpretation and chronically elevated liver enzymes. Chart review was done for 332 patients, the one with missing data were excluded (n=16). We included 316 patients in the analysis. Of them 12.0% patients had underlying chronic liver disease. Results: Of total 43.7% were female and 48.4% were Caucasians. The patients with liver disease were older (64.6 ± 15.3 vs 57.6 ± 17.4, p=0.02) as compared to non-CLD. The CLD patients had higher number of coronary artery disease (47.4% vs 18.9%, p<0.001). The other comorbid conditions including chronic obstructive pulmonary disease, asthma, cancer, chronic kidney disease, diabetes mellitus, hypertension, obesity, obstructive sleep apnea and smoking were similar in both groups. The CLD patients had higher mortality (aOR: 3.3, 95% CI: 1.37-8.05), thromboembolism (aOR: 3.77, 95% CI: 1.33-10.71), acute respiratory distress syndrome (aOR:2.25, 95% CI: 1.04-4.85) and trend of severe COVID-19 infection (aOR:1.90, 95% CI:0.91-3.98) whereas the 3 month readmission was similar in both groups. The Kaplan Meier survival curve suggest that COVID-19 patients with CLD died early during the study period. Conclusion: The presence of chronic liver disease in inpatient COVID-19 infections is associated with three fold higher mortality. The CLD patients had higher incidence of severe infection. $Φgure

4.
European Heart Journal ; 42(SUPPL 1):3084, 2021.
Article in English | EMBASE | ID: covidwho-1553849

ABSTRACT

Introduction: The COVID 19 pandemic has led to a dramatic rise in the use of Telehealth. Studies have shown racial/ethnic disparities in internet access, a basic prerequisite for telehealth. However, little is known on the extent of this digital divide amongst racial minorities with cardiovascular comorbidities. Purpose: To investigate racial disparities in internet access amongst those with cardiovascular diseases and risk factors, and explore the degree to which this exists amongst those with different levels of comorbidities. Methods: Behavioral Risk Factors Surveillance System data from the years 2013-2017, during which survey respondents were asked the main outcome of interest (Have you used the internet in the past 30 days) were pooled. Respondents were included if they responded yes to questions on selected cardiovascular diseases and risk factors of interest. Multivariable logistic regression was used to analyze the odds of internet use by racial groups adjusting for several socioeconomic factors. Results: There were a total of 1,478,214 individuals representing 150,235,244 million adults (non-Hispanic Blacks 11.31% and Hispanics 13.75%). Hispanics and Non-Hispanic Blacks reported the lowest prevalence of internet use (66.1% and 64.4% respectively) compared to Non- Hispanic Whites (81.9%). On regression analysis, racial minorities consistently reported lower rates of internet use, averaging 50% lower odds compared to non-Hispanic Whites. Results remained statistically significant even after controlling for several sociodemographic variables. Conclusion: Using a large nationally representative cohort, we demonstrated differences in internet access amongst racial minorities and those with multiple comorbidities, placing them at distinct disadvantage with access to telecare. Our study adds to a growing body of literature that shows the disproportionate impact of the pandemic on minorities and calls for a concerted effort to reduce disparities in healthcare delivery.

5.
Int. Conf. Electr., Telecommun. Comput. Eng., ELTICOM - Proc. ; : 210-214, 2020.
Article in English | Scopus | ID: covidwho-960712

ABSTRACT

In epidemic situations such as the novel coronavirus (COVID-19) pandemic, face masks have become an essential part of daily routine life. The face mask is considered as a protective and preventive essential of everyday life against the coronavirus. Many organizations using a fingerprint or card-based attendance system had to switch towards a face-based attendance system to avoid direct contact with the attendance system. However, face mask adaptation brought a new challenge to already existing commercial biometric facial recognition techniques in applications such as facial recognition access control and facial security checks at public places. In this paper, we present a methodology that can enhance existing facial recognition technology capabilities with masked faces. We used a supervised learning approach to recognize masked faces together with in-depth neural network-based facial features. A dataset of masked faces was collected to train the Support Vector Machine classifier on state-of-the-art Facial Recognition Feature vector. Our proposed methodology gives recognition accuracy of up to 97% with masked faces. It performs better than exiting devices not trained to handle masked faces. © 2020 IEEE.

SELECTION OF CITATIONS
SEARCH DETAIL