Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 7 de 7
Filter
1.
AIP Conference Proceedings ; 2779, 2023.
Article in English | Scopus | ID: covidwho-20241847

ABSTRACT

Today, the whole world is fighting the war against Coronavirus. The spread of the virus has been observed in almost all the parts of the world. Covid-19 also known as SARS-Cov-2 was initially observed in China which rapidly multiplied all over the world. The disease is said to spread by cough, normal cold, sneezing or when a person is in close contact with someone who is already infected. Therefore, the spread of the virus can occur when there is direct contact with an infected person or with the objects touched by the infected person. Hence, it is important to detect the contiguous spread of the virus and control it by taking appropriate measures. Several deep learning models have been used in detecting many diseases like Malaria disease, Lung infection, Parkinson's disease etc. Likewise, CNN model along with other transfer techniques is best proven to detect whether a person is infected with covid positive or not. The dataset consists of 1000 images of covid positive and normal x-rays. The proposed model has been trained and tested on the image dataset with the help of transfer learning models in order to improve the performance of the model. The models VGG-16, ResNet-50, Inception v3 and Xception have achieved an overall accuracy of 93%,82%,96% and 92% respectively. The performance of all the 4 architectures are analyzed, understood and hence presented in this paper. It is hence important to classify and detect covid positive infection and contribute towards making the world Covid-free. © 2023 Author(s).

2.
European Journal of Molecular and Clinical Medicine ; 10(1):4750-4754, 2023.
Article in English | EMBASE | ID: covidwho-2245365

ABSTRACT

Introduction: Dengue viral infection is an arboviral disease which is transmitted by Aedes aegypti and Aedes albopictus. Dengue cases are now increasing a global burden especially in tropical and subtropical countries.1 The patients with dengue fever have high levels of nonstructural protein-1 (NS1) protein in their serum after onset till <5 days. The present study aims to establish most sensitive and reliable method for the early diagnosis of dengue infection. Materials & Methods: Total 110 patients were screening who were having <5 days of history of dengue like fever at NIMS Medical College, NIMS University, Jaipur from June 2020 to Oct 2022. For Dengue NS1 ICT & ELISA J. Mitra Pvt Ltd. Kits were used. Dengue RTPCR was done by TRU PCR 3B Black Bio kits as per standard protocol.5 Results: Out of 110, total 72 (65.45%) cases were positive (either by ICT, ELISA & RTPCR). Among 72 dengue positive cases 48 (66.6%) were male while 24 (33.4%) were females. Male: female ratio was 2:1 observed. 55 patients were positive by Dengue NS1 ICT, 59 were positive by NS1 ELISA while 72 cases were positive by RTPCR. Conclusion: Early detection and diagnosis are very important in the case of dengue infection as if it is not treated it may lead to many complications. RTPCR is the most sensitive and specific method for the early diagnosis of dengue. After this covid pandemic most hospitals have RTPCR lab facilities which can be utilized for dengue detection by RTPCR.

3.
Indian Journal of Public Health Research and Development ; 13(4):213-216, 2022.
Article in English | EMBASE | ID: covidwho-2081579

ABSTRACT

Background: In recent decades, the prevalence of fungal sinus infection has increased. It's plausible that this is related to increased awareness, antibiotic usage, and the use of immunosuppressive drugs. Furthermore, much has been written on the involvement of fungus as a causative organism. Objective(s): To identify fungal pathogens and correlate laboratory findings with clinical findings. Material(s) and Method(s): Patients with AIFR following recent COVID-19 infection were included. After performing potassium hydroxide (KOH) wet mounts, post-operative material was collected and cultured on two tubes of Sabouraud dextrose agar (SDA) and stored at 250 C and 370 C for isolation and identification. Result(s): Out of 329 diabetic individuals with AIFS following COVID-19 infection, 51% exhibited mucopurulent discharge and 75.6 % had unilateral involvement. Only 57.4% of KOH mount samples were positive for fungal components, however 76.3% of SDA samples exhibited positive growth, with 62 % Mucorales, 8% Aspergillus, and 6 % Candida species. Conclusion(s): Mucor mycosis can develop in COVID-19 patients, particularly those with diabetes, a high and imprudent use of corticosteroids, and invasive ventilation. KOH test resulted in a preliminary diagnosis, whereas Culture remains the gold standard for identification. Copyright © 2022, Institute of Medico-legal Publication. All rights reserved.

4.
Indian Journal of Medical Microbiology ; 39:S66-S67, 2021.
Article in English | EMBASE | ID: covidwho-1734495

ABSTRACT

Background:COVID-19 caused by SARS CoV 2 has emerged into a global pandemic. Paediatric COVID-19 infection is rela- tively mild when compared to adults, and children are reported to have a better prognosis. Mortality in children appears rare. Many infected children are often asymptomatic and remain undiagnosed without population screening. Due to these reasons children can be potential source of infection and may lead to higher transmission. Therefore knowledge on prevalence of asymptomatic and symptomatic cases among children is essential for effective control of COVID Methods:Nasopharyngeal Samples received at VRDL which were collected from children from 1st June to 30th Novem- ber of 2020 were subjected to RT-PCR for detection of SARS CoV-2 RNA and the Positive cases were correlated with the clinical information submitted along with the samples Results:Among the samples of children received and analysed at VRDL in three months, 343 tested positive for COVID - 19, of which 129 (37.60%) cases were symptomatic and 214(62.3%) were asymptomatic. Among the symptomatic cases, 25(19.3%) cases were diagnosed with SARI. Fever was the most common non respiratory symptom seen. The results of the remaining three months will be produced at the time of the presentation Conclusions:Knowing the prevalence of asymptomatic and symptomatic cases of COVID-19 among children helps in making strategies for effective control of COVID-19

5.
Indian Journal of Medical Microbiology ; 39:S56, 2021.
Article in English | EMBASE | ID: covidwho-1734459

ABSTRACT

Background: COVID-19 caused by a novel coronavirus (SARS- COV-2) has emerged as a global pandemic. There is a con- tinuous debate whether to consider allergic respiratory disorders as protective factor or as a risk factor for COVID -19. At the same time severity of COVID 19 is found to be more if patient’s level of disease control is poor according to some studies. Hence there is a need to find the prevalence of allergic respiratory diseases among COVID 19 positive cases. HCW are taken as the study population as they have equal COVID exposer risk and also good level of disease control. AIM: To find the prevalence of allergic respiratory diseases among COVID positive HCW. Methods: Nasopharyngeal samples of HCW collected from May 15 to November 15 2020 were subjected to RT PCR for detection of SARS COV -2 RNA and the positive cases were noted for history of allergic respiratory disorders like chronic rhinosinusitis, asthma from the clinical information provided while sample collection. Results: Out of total 912 Health Care Workers tested for COVID 19 in first 5 months by RT PCR 121 were COVID positive, among them 24(19.8%) have known history of allergic respiratory diseases of which 4(3.3%) were known for Chronic Rhinosinusitis, 15(12.3%) were asthmatic, 5(4.13%) have both CRS and asthma, further results will be provided at the time of presentation. Conclusions:Prevalence of allergic respiratory diseases helps in finding out if it’s a risk factor or not and also if any pro- tective role against COVID 19 to help in further studies

6.
5th International Conference on Trends in Electronics and Informatics, ICOEI 2021 ; : 1468-1472, 2021.
Article in English | Scopus | ID: covidwho-1393732

ABSTRACT

COVID-19 pandemic has bought a lot of change in our daily routine. To protect ourselves from getting infected, we need to follow certain precautions. One such safety measures are wearing a face mask. Viruses spread from one person to other respiratory droplets. When an infected person talks, shouts, sneezes or coughs, the droplets land in the mouth or nose of other people who are nearby. So, wearing a face mask over nose and mouth acts as a barrier for preventing the transmission of respiratory droplets. But many people ignore wearing a mask in public areas. It is good to have a system to identify people without masks in public places. This system, when integrated with embedded systems ensures the public safely. Our project aims to detect the people without masks on a video by developing a machine learning algorithm which identifies the person without a face mask. Machine learning is one of the techniques of Artificial Intelligence which is used for extracting valuable knowledge from large databases[1]. We collected the training sets from Kaggle, few open-source libraries and Google consisting of faces with and without a face mask. There are around 1500 images of with and without a face mask. © 2021 IEEE.

7.
7th International Conference on Advanced Computing and Communication Systems, ICACCS 2021 ; : 459-465, 2021.
Article in English | Scopus | ID: covidwho-1280209

ABSTRACT

The Novel Coronavirus 2019 (COVID-2019) spread quickly around the planet and turned into an undermining pandemic. The early detection of Covid disease is one of the principal challenges and needs on the planet. Early detection helps in controlling the spread of infection. Deep learning has acquired great significance in clinical picture investigation, illustrating improved performance compared to conventional machine learning framework. In this work, a DL based model is proposed for recognizing and characterizing the inconsistencies in chest X-Ray pictures and arranging as unaffected, Covid affected, or Pneumonia. Considering the information inadequacy in clinical space, VGG architecture is utilized as the pre-trained models for building the model for recognition. The quality of the X-Ray pictures and noise present in the pictures influence the decision making leading to high false positives and false negatives. In the current model, pre-processed pictures are fed as input to the DL model accomplishing a maximum accuracy of 96.56%. The proposed model outperforms the DL model without pre-processing with a false positive rate of 0.024 and a false negative rate of 0.026. © 2021 IEEE.

SELECTION OF CITATIONS
SEARCH DETAIL