Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 11 de 11
Filter
1.
5th International Conference on Electrical, Electronics, Communication, Computer Technologies and Optimization Techniques, ICEECCOT 2021 ; : 137-144, 2021.
Article in English | Scopus | ID: covidwho-1769612

ABSTRACT

According to the World Health Organization(WHO), the Coronavirus Disease 2019 (COVID-19) is a global hazard to the healthcare sector, with developing and highly populated countries like India influencing the country's rising economy. In this situation, early detection and diagnosis of COVID-19 are critical for mitigating the pandemic's impact COVID-19 is critical for mitigating the damage induced by the pandemic disease;consequently, alternate methods for detecting COVID-19 other than manual lab-Testing are necessary. This work aims to build and deploy deep Convolutional Neural Networks(CNN) image classification models to a python-flask based web app which is hosted on AWS-EC2 Linux based virtual server to predict if a person is COVID-19 positive or negative just by uploading chest X-ray or computed tomography(CT)-scan image therefore, this method investigates the potential of Deep Transfer Learning algorithms such as Res Net 50, Inception V3, Xception, and VGG16 to act as an alternative for manual lab-based testing like reverse-Transcription polymerase-chain-reaction(RT-PCR)tests, Rapid tests, and other various types of Antigen tests which, on average, takes 1-2 days to acquire the results, which is unbearable because the affected person can spread the disease to many more members of the population the CNN models employed in this work are trained on chest X-rays and CT-scan image datasets obtained from verified radiologists' sources, then these datasets are preprocessed and normalized to achieve higher efficiency. Finally, these trained models are integrated with web-scripting files to create user-friendly web platform, allowing users to upload the sample of the chest X-ray or CT-scan image to refer and compare the predictions made by all four types of models on a single web plat form within a few minutes. © 2021 IEEE.

2.
2nd IEEE International Conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2021 ; 2021.
Article in English | Scopus | ID: covidwho-1746125

ABSTRACT

Artificial Intelligence is a process that enables machines to imitate human behaviour. Both Machine Learning and Deep Learning are subsets of AI. The basic difference between ML(Machine Learning) and DL(Deep Learning) is that in Machine Learning manually defining of features is done to get the desired outcome whereas in deep learning the neural network learns of its own and publishes the result. In the present crisis due to COVID-19 pandemic the contagious power of virus has led to huge encounter of cases on daily basis. This stimulates the need for specialised and accurate methods to detect COVID-19 cases. The contribution of deep learning to this problem has been significant. The application of deep learning concepts has shown its emence importance and utility in medical domain for detection of COVID-19 cases using CT scan and X-Ray images of lungs. Our proposed method compares the accuracy of multiple pretrained models in predicting COVID-19 infected cases for a specific dataset of radiological images using three distinct optimizers for each model. This research aims to determine which model, together with its associated optimizer, is most suitable for identifying COVID-19 infected cases from radiological lungs images. © 2021 IEEE.

3.
Indian Journal of Medical Microbiology ; 39:S62, 2021.
Article in English | EMBASE | ID: covidwho-1734480

ABSTRACT

Background:COVID-19 RT-PCR kits of various manufacturers categorize certain samples as inconclusive and repeat testing or re-sampling is advised in those cases to ascertain positivity or a negative result. This is of paramount im- portance because a definite result helps in effective implementation of public health measures, leading to implicit con- tainment. Our study aims to ascertain criteria through which the inconclusive can be definitively categorized as either positive or negative. This will be of help in conserving manpower and resources which are utilized in re -testing of pa- tients with inconclusive RT-PCR result. Methods:Hundred samples which were inconclusive (IC) as per Q-Line Covid-19 RT-PCR kit from 1st September, 2020 to 31st October, 2020 were included in the study. These were classified into 4 groups based on Ct value of N gene;namely A (<25;3 samples), B (25-30.9;31), C (31-34;62) and D (>34;4) and were tested by NIV kit. RNA extracts of these sam- ples were run through ICMR-NIV rRT-PCR screening and confirmatory assay to ascertain a criteria with which inconclu- sives can be definitively reported as either positive or negative. Results:Majority (62%) of IC samples were in group C (Ct 31-34) followed by 31% in group B, 4% in D and 3% in group A (<25). Confirmed positivity by NIV kit was 100% in group A and 51.6%, 20.96% and 25% respectively in B, C & D groups.29% of group B and 24% group C samples remained inconclusive by NIV kit. Majority of confirmed negatives were found in group D (75%), followed by group C (54.83%). Conclusions:All inconclusive samples with Ct values of N gene less than 25 were positive with ICMR -NIV kit, whereas >50% of samples of Ct >30 became negative. Repeat sampling could be avoided in 76% cases by following strategy of repeat testing in NIV kit.

4.
Indian Journal of Medical Microbiology ; 39:S60, 2021.
Article in English | EMBASE | ID: covidwho-1734473

ABSTRACT

Background:The Coronavirus disease 2019 (COVID 19) pandemic has resulted in reduced performance of non-emergent surgeries and procedures across the nation. About four-fifth of COVID-19 infections remain asymptomatic. With an incu- bation period of 7-14 days, patients can also remain in the pre-symptomatic stage. Hence, knowledge of the prevalence of disease among the asymptomatic is important to prevent spread of disease to the health care professional as well as for patient safety. The present study sought to assess the frequency of positivity of COVID 19 among pre -procedural/pre-operative patients. Methods:A retrospective study of all asymptomatic pre-procedural cases was conducted from 10th June 2020 till 10th November 2020. Nasal swabs were collected from patients 48 hours before procedures (including elective and emer- gency surgeries, patient scheduled to receive chemotherapy, radiotherapy, patients undergoing biopsy, endoscopy). RT - PCR test was done for all samples. Case-specific data, results of all PCR tests, and answers to screening questions (about symptoms, exposure, and travel) were obtained Results: 5320 tests were conducted during the study period. Of these, data could be analysed for 2117 tests done. 51.1% were male patients and the median age group of the cohort was 46 years. 254 of 2117 (11.9%) belonged to the paediatric age group. Of 2117, 35 samples were rejected because of sample leakage or improper labelling. Out of the remaining 2082 samples;338 were positive;1606 were negative, and 138 inconclusive. We received second sample for 117 of the 138 inconclusive samples of which 18 were positive, 93 were negative and 6 remained inconclusive. Thus, the total positivity was 17.1%. Conclusions:This study confirms the high proportion of asymptomatic patients with COVID -19 positivity;and suggests the value of screening by RT-PCR during COVID-19 pandemics.

5.
Indian Journal of Medical Microbiology ; 39:S59, 2021.
Article in English | EMBASE | ID: covidwho-1734470

ABSTRACT

Background:From the day of the detection of 1st case in India on 30th January 2020, COVID -19, has infected 8.96 mil- lion people in India, from around 128 million samples tested. The clinico -epidemiological characteristics of COVID 19 have been varied in different countries. The present study was undertaken to understand the clinico -epidemiological characteristics of COVID-19 in Odisha. Methods:This was a retrospective, single centre study. The epidemiological, demographic & clinical parameters were analysed of the samples tested in AIIMS Bhubaneswar between March 2020 to November 2020. Results:A total of 56,547 samples were tested for SARS CoV-2 by RT-PCR from March 24th 2020 till 15th November 2020. Of the total samples tested, 9754 were tested positive, with an average positivity rate of 17.25%. The mean age of the patients 38.21 years, with male to female ratio of 3:1. Among the various age groups, the majority affected were the middle ages (31-50 years) constituting around 38.77% (n = 3782) of the total cases followed by 15 -30 years (31.48%, n=3071) &> 50 years (23.64% n = 2305) & was least in children (<14years) with 6.11% (n = 596). Among the COVID -19 positives, 64.5% (n=6295) were asymptomatic & only 35.5% (n=3459) were symptomatic. Of the symptomatic patients, 81.1% (n=2805) presented with mild, 17.7 %( n=612) cases moderate, and only around 1.12% (n=39) had severe COVID - 19 disease. Of the severe cases, majority belong to the age group 31-50 (38.46%, n = 17), followed by 15-30 (15.3%, n=11). The monthly trend showed an increasing trend up to September, with maximum positivity rate of 38%, followed by a decline during October (14.7%) & November (5.8%) Conclusions: In this study of 9754 patients with confirmed COVID-19 in Odisha, the characteristic findings included younger age, male predominance, high proportion of asymptomatic patients & a declining trend in the positivity rate over the months

6.
Indian Journal of Medical Microbiology ; 39:S58, 2021.
Article in English | EMBASE | ID: covidwho-1734466

ABSTRACT

Background:COVID-19 pandemic is posing a major burden on society. Measures taken to reduce its spread critically de- pend on timely and accurate identification of virus-infected individuals by the most sensitive and specific method availa- ble, i.e. real-time reverse transcriptase PCR (RT-PCR). RT PCR can detect SARS-CoV-2 as early as day one of symptom onset. There are various RT PCR kits approved by FDA & ICMR, performance of which vary widely. Here, we assessed the performance of four PCR kits with the ICMR NIV Screening & Confirmatory assay used for diagnosis of COVID -19 in Od- isha. Methods:A total of 20 samples, which included five positives, one inconclusive & 14 negative samples by NIV assay were evaluated in the four commercially available RT-PCR kits ie;Q-line Molecular (Q-line), Allplex™ 2019-nCoV Assay (Allplex), Liferiver Novel Coronavirus (COVID-19) Multiplex RT PCR (Liferiver), LabGun™ COVID-19 kit (LabGun). Results:The sensitivity of the four PCR kits varied with the high cycle threshold (Ct) value (30-35 by NIV) & the lower Ct value (<30 by NIV). Among the negative results of NIV (n=14), LabGun, Allplex kits showed 100% concordance, while Q - line & Life river were shown to have 92.8% & 50% concordance respectively. In the inconclusive results (n=1), only All- plex Assay documented a concordance of 100% with the NIV assay, while the Q -line (n=6) & Life river (n=7) showed higher number of inconclusive results. The different kits showed lesser variations with positive results (n=5), with Life river, Allplex & LabGun showing 100% concordance for positive results with NIV assay. However, Q -line was able to de- tect only 1 positive out of all positives. Conclusions:PCR kits vary in sensitivity & it is imperial to evaluate the various kits in order to deliver accurate results at optimum time in order to detect the cases to initiate adequate treatment & control measures

7.
Indian Journal of Medical Microbiology ; 39:S40-S41, 2021.
Article in English | EMBASE | ID: covidwho-1734455

ABSTRACT

Background:During the ongoing COVID19 pandemic period, any new cases of acute-onset respiratory illness are likely to be treated as suspected COVID-19 by default. Methods:A 42year-old lady was admitted with a 4-week history of fever and cough, followed by a 4-days history of increasing short- ness of breath. Fever was intermittent, high grade and was associated with chills and rigor. The patient had a history of uncontrolled type II diabetes mellitus and on admission HbA1C was 15.5%. On examination she had a temperature of 102° F, blood pressure (BP) of 101/67mm Hg, heart rate of 130 beats per minute, respiratory rate (RR) of 24 breaths per minute and O2 saturations of 92% in room air. On respiratory examination, there were crackles in the left infrascapular and infraaxillary area. The patient was admitted in the COVID suspect ward with an impression of moderate COVID-19 infection and nasopharyngeal swab was sent for SARS-CoV-2 on RT-PCR. The patient underwent a CECT scan of thorax, abdomen and pelvis that revealed consolidation in bilateral lung fields with a cavity in lingular lobe with presence of air-fluid level. Mediastinal and hilar lymphadenopathy were present. [Formula presented] Results: SARS-CoV-2 RT-PCR was negative. The patient’s sputum sample revealed pure growth of purple, flat, dry, wrinkled colonies on Ashdown agar after 48 hours which was identified as Burkholderia pseudomallei. The Isolate was susceptible to ceftazidime, mero- penem, co-trimoxazole, amox-clav and chloramphenicol. The patient was started on I.V Meropenem 500mg every 8hourly for 21 days and was discharged on co-trimoxazole tablet. Conclusions: The case definitions of COVID-19 such as fever, cough and shortness of breath can be associated with other infectious etiologies. The role of the microbiology laboratory is thus very crucial in COVID-19 from overshadowing other infec- tious diseases, particularly in endemic areas, hence preventing misdiagnosis and consequent adverse outcomes for patients.

8.
Journal of Association of Physicians of India ; 70(2):28-31, 2022.
Article in English | Scopus | ID: covidwho-1728047

ABSTRACT

Objective: This study intends to compare the clinical characteristics and the prevalence and spectrum of bacterial pathogens in COVID-19 patients admitted to ICU during the first and second waves at a tertiary care, teaching and referral hospital of eastern India. Method: This is a hospital-based retrospective study which analysed demographic details, clinical profile and bacterial culture results of severe and critically ill COVID-19 patients admitted in intensive care units (ICU) during April -Oct 2020 (1stwave) and April -July 2021 (2ndwave). Result: The patients admitted during the 2ndwave were comparatively older and had multiple comorbidities compared to the 1stwave. (23.8%) (45/189) and 50% (173/346) of the COVID-19 patients admitted to ICU developed bacterial infection during the 1stand 2ndwave respectively. Overall, there was predominance of multidrug resistant Gram negative bacilli in both the waves. There was increased isolation of intrinsic colistin resistant microorganisms. Conclusion: Multidrug resistant Gram negative bacterial infections, remain a dreaded complication in severe and critically ill hospitalised COVID-19 patients requiring ICU care and high usage of colistin spirals the emergence and spread of pathogens intrinsically resistant to colistin. © 2022 Journal of Association of Physicians of India. All rights reserved.

9.
Journal of NeuroInterventional Surgery ; 13(SUPPL 1):A63-A64, 2021.
Article in English | EMBASE | ID: covidwho-1394197

ABSTRACT

Introduction COVID-19 infection has been associated with an increased risk of thrombotic events, including cerebrovascular accidents, presumed to be secondary to a systemic hypercoagulable state. These events have been reported even in young patients, without other significant vascular risk factors. We present a different, atypical case of a large-vessel occlusion (LVO) acute ischemic stroke secondary to a focal vasculopathy in a young patient with COVID-19 infection, requiring mechanical thrombectomy and emergent intracranial stenting, and we also review available literature. Methods Case analysis and literature review. Results A patient in their early 20's with mild obesity presented to the emergency department (ED) one hour after acute onset of left hemiplegia (NIHSS 11). Emergent imaging revealed multifocal right middle cerebral artery territory acute ischemic infarcts with small petechial hemorrhage. CT angiography showed a right M1 segment occlusion. He was not a candidate for intravenous thrombolysis. Patient underwent mechanical thrombectomy with contact aspiration. The occluded right M1 segment was successfully recanalized, but follow-up angiography revealed re-stenosis. Balloon angioplasty was performed, but repeat angiography again demonstrated critical re-stenosis. A balloon-mounted stent was placed in the R M1 segment, with successful recanalization and no further restenosis. The patient was acutely loaded with intravenous tirofiban, followed by oral aspirin and clopidogrel. Notably, the patient tested positive for COVID-19, but remained otherwise asymptomatic. Laboratory investigation, including hypercoagulabe and autoimmune workup for typical and atypical stroke etiologies, did not reveal any significant abnormalities, but the patient did have mildly elevated d-Dimer, and a minimally elevated homocysteine levels. Lower extremity ultrasound was negative for deep venous thrombosis, and echocardiogram was negative for significant abnormalities or intracardiac shunts. No cardiac arrhythmia was found. Patient was discharged home on hospital day five with NIHSS 1 (mild left facial droop) on aspirin and clopidogrel. At a two-month follow-up, patient remained without any objective residual deficits. Transcranial Doppler ultrasound at follow-up revealed full patency of the intracranial stent. Our literature search revealed a large body of evidence for acute stroke, LVO and secondary hypercoagulable state in COVID patients. However, focal vasculopathy, occasionally described with other viral infections such as VZV, has not been reported in association with COVID infection. Conclusion To our knowledge, our case is the first to illustrate the potential for COVID-19 infection to present as a focal intracranial vasculopathy in an otherwise healthy youngpatient, resulting in acute ischemic stroke without an underlying hypercoagulable state. Rescue intracranial stenting was necessary to maintain vessel patency and restore intracranial flow.

10.
Journal of NeuroInterventional Surgery ; 13(Suppl 1):A63-A64, 2021.
Article in English | ProQuest Central | ID: covidwho-1327708

ABSTRACT

IntroductionCOVID-19 infection has been associated with an increased risk of thrombotic events, including cerebrovascular accidents, presumed to be secondary to a systemic hypercoagulable state. These events have been reported even in young patients, without other significant vascular risk factors. We present a different, atypical case of a large-vessel occlusion (LVO) acute ischemic stroke secondary to a focal vasculopathy in a young patient with COVID-19 infection, requiring mechanical thrombectomy and emergent intracranial stenting, and we also review available literature.MethodsCase analysis and literature review.ResultsA patient in their early 20’s with mild obesity presented to the emergency department (ED) one hour after acute onset of left hemiplegia (NIHSS 11). Emergent imaging revealed multifocal right middle cerebral artery territory acute ischemic infarcts with small petechial hemorrhage. CT angiography showed a right M1 segment occlusion. He was not a candidate for intravenous thrombolysis. Patient underwent mechanical thrombectomy with contact aspiration. The occluded right M1 segment was successfully recanalized, but follow-up angiography revealed re-stenosis. Balloon angioplasty was performed, but repeat angiography again demonstrated critical re-stenosis.. A balloon-mounted stent was placed in the R M1 segment, with successful recanalization and no further restenosis. The patient was acutely loaded with intravenous tirofiban, followed by oral aspirin and clopidogrel. Notably, the patient tested positive for COVID-19, but remained otherwise asymptomatic. Laboratory investigation, including hypercoagulabe and autoimmune workup for typical and atypical stroke etiologies, did not reveal any significant abnormalities, but the patient did have mildly elevated d-Dimer, and a minimally elevated homocysteine levels. Lower extremity ultrasound was negative for deep venous thrombosis, and echocardiogram was negative for significant abnormalities or intracardiac shunts. No cardiac arrhythmia was found. Patient was discharged home on hospital day five with NIHSS 1 (mild left facial droop) on aspirin and clopidogrel. At a two-month follow-up, patient remained without any objective residual deficits. Transcranial Doppler ultrasound at follow-up revealed full patency of the intracranial stent. Our literature search revealed a large body of evidence for acute stroke, LVO and secondary hypercoagulable state in COVID patients. However, focal vasculopathy, occasionally described with other viral infections such as VZV, has not been reported in association with COVID infection.ConclusionTo our knowledge, our case is the first to illustrate the potential for COVID-19 infection to present as a focal intracranial vasculopathy in an otherwise healthy young-patient, resulting in acute ischemic stroke without an underlying hypercoagulable state. Rescue intracranial stenting was necessary to maintain vessel patency and restore intracranial flow.DisclosuresA. Mahapatra: None. A. Witek: None. G. Toth: None.

11.
Turkish Journal of Physiotherapy and Rehabilitation ; 32(2):1785-1793, 2021.
Article in English | Scopus | ID: covidwho-1218844

ABSTRACT

The progressing COVID-19 flare-up has caused a worldwide calamity with its lethal spreading. The infection spreads rapidly and is a threat to humankind. Seeing the need of great importance, one should consistently play it safe of which one being social distancing. Social distancing is considered to be the most suitable measure against the powerful COVID-19 affliction. As per the WHO, to practise appropriate social distancing, individuals should keep 3ft or 1m distance between one another. This framework centres around an answer for determining social distancing utilizing YOLO object discovery on video film and pictures continuously. The system utilizes the YOLOv5 object detection to distinguish people in a video. The detection model distinguishes people groups utilizing recognized bounding box data. The pairwise distances of the centroid of the distinguished bounding boxes of the individuals are resolved using the Euclidean distance. To detect the social distance infringement between individuals, we are utilizing an estimate of the actual distance to pixel and setting and edge. An infringement edge is set up to assess whether the distance esteem breaks the base social distance limit. The framework ensures higher derivation speed and is subsequently fit for conveying real-time outcomes withoutlosing on precision, even in much complex arrangements. © 2021 Turkish Physiotherapy Association. All rights reserved.

SELECTION OF CITATIONS
SEARCH DETAIL