Your browser doesn't support javascript.
Show: 20 | 50 | 100
Results 1 - 20 de 122
Filter
1.
Supportive Care in Cancer ; 30:S41, 2022.
Article in English | EMBASE | ID: covidwho-1935781

ABSTRACT

Introduction A global trial is currently investigating the impact of high-intensity interval training (HIIT) on survival in advanced prostate cancer (the INTERVAL trial). To ensure greater accessibility, we designed a parallel trial (EXACT), to determine the feasibility of exercise in those contraindicated to HIIT. Methods Men with metastatic castrate-resistant prostate cancer being actively treated with androgen deprivation therapy and a novel hormone therapy (abiraterone acetate or enzalutamide) are eligible to participate in 12- weeks of home-based walking and strengthening. Participants complete physical (e.g. 6-min walk test and timed sit-to-stand) and quality of life (e.g. BPI-SF;EQ-5D-5L;FACIT-fatigue;FACT-P) outcomes at baseline (T1), 12 (T2) and 24 weeks (T3). This trial was adapted to enable remote recruitment and delivery during the COVID-19 pandemic. Results To date, 118 patients have been screened, with 33 approached by their clinician to participate. 25 patients have consented, with 12 completing the trial without any intervention-related adverse events and 6 withdrawn. Recruitment and trial delivery was operational throughout the COVID-19 pandemic. Currently positive trends are evident for physical and quality of life outcomes at T2 and T3. Conclusions Although this trial is ongoing, early trends suggest this intervention is safe and feasible for men with advanced castration resistant prostate cancer and could improve physical capacity and quality of life.

2.
National Journal of Physiology, Pharmacy and Pharmacology ; 12(7):916-920, 2022.
Article in English | EMBASE | ID: covidwho-1928811

ABSTRACT

Background: There are numerous studies indicating that COVID-19 pandemic has brought a great deal of pressure for medical fraternities, as medical teachers and students were busy saving lives. The mental health of these frontiers and medical education both suffered. Aims and Objectives: This study aims to determine the assessed pooled prevalence of depression among medical students of India by undertaking meta-analysis of published original research studies during pandemic. Materials and Methods: Researcher followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses. Authors used terminologies such as depression, mental health, medical students, and India to search PubMed and Google Scholar databases for original articles published between January 2020 and March 2022 based on mental health of Indian medical students. Researcher had chosen only the Depression, Anxiety, and Stress Scale 21 items based study to prevent false heterogenicity. Results: Out of 1471 screening, a total of six original research articles were included after screening for eligibility criteria involving 3248 medical students from different medical colleges of India. The median number of students was 541.33 (range, 181–2021). Meta-analysis of pooled prevalence assessment of depression among medical students in India by random effects model was 38% (confidence interval: 27–49%). Conclusion: Within study limitations, the high prevalence of depression was noted among medical students of India.

3.
2nd International Conference on Computational Methods in Science and Technology, ICCMST 2021 ; : 287-292, 2021.
Article in English | Scopus | ID: covidwho-1922669

ABSTRACT

COVID-19 became the headlines of every nation because of its unrivalled transmission speed and outbreaks in humans, but its new variants are raising new challenges after every few months iteratively. Keeping track of travel history and maintaining a record of people coming in contact with any COVID affected individual has become a prime concern to control the spread of this pandemic disease. The existing tracking system lags in fetching records of people who came in contact with the affected one and maintaining travel history across the local boundaries of the cities. In this position paper, we are proposing a framework for an IoT driven blockchain (BC) based secured tracking system that gathers users' travel and meeting history, and it may help with remote health monitoring. The data gathered for the same is treated as immutable and achieves interoperability with the help of Smart Contracts (SC). It could be proved as a useful framework for post COVID-19 economic revival with the help of an IoT driven blockchain based secured model for remote health monitoring & chain tracking. © 2021 IEEE.

4.
JOURNAL OF CLINICAL AND DIAGNOSTIC RESEARCH ; 16(6):UC43-UC47, 2022.
Article in English | Web of Science | ID: covidwho-1912145

ABSTRACT

Introduction: There are various researches for increased anxiety in Coronavirus Disease 2019 (COVID-19) patients and their relatives due to separation, but most of them are observational. Audio-video communication can be employed for communication between patients in rigorous isolation and their relatives. There were few researches available about the effectiveness of video calling on anxiety in COVID-19 patient. Gujarat lags considerably behind, according to bibliometric analysis of the India-based COVID-19 publication. Thus, the authors sought to conduct present study to evaluate that how video conferencing between COVID-19 patients in isolation and their relatives, affects anxiety. Aim: To determine the effect of standardised virtual communication on anxiety levels in relatives of COVID-19 intubated patient's. Materials and Methods: This prospective interventional study was conducted at a tertiary care centre, Gujarat Medical Education and Research Society Medical College and Hospital, Vadodara, Gujarat, India, from April 2021 to July 2021. Total 283 relatives of COVID-19 patient were recruited by purposive sampling. Virtual communication unit was set up, where relatives can communicate audio-visually with their patient and caregiver with help of video calling technology. Inside Intensive Care Unit (ICU), the caregivers (intern, doctors or nurses) wearing Personal Protective Equipment (PPE) kit handled the portable audio-visual screen and answered on behalf of the patient. The Hamilton anxiety scale was used to measure the anxiety of relatives before and after the communication. Paired t-test was used to statistically analyse the data. Level of significant p-value <0.05 was considered. Results: A total of 283 subjects with 178 males and 105 female relatives were enrolled in the study. As an effect of communication, the mild anxiety prevalence decreased from 69.71% to 46.27%, the moderate anxiety prevalence decreased from 4.93% to 3.81%, and 49.92% of relatives reported being anxiety-free after communication. Statistical analysis of the paired t-test of Hamilton anxiety score showed a drop in anxiety score after communication from 4.77 +/- 3.66 to 2.88 +/- 2.34 (p-value <0.001). Conclusion: Audio-visual technology is effective as a mode of communication and counselling during a pandemic to reduce anxiety in COVID-19 victim families.

5.
JOURNAL OF INDIAN ASSOCIATION OF PUBLIC HEALTH DENTISTRY ; 20(2):153-158, 2022.
Article in English | Web of Science | ID: covidwho-1911868

ABSTRACT

Background: Novel coronavirus pandemic has emerged as a grave global health crisis. The pandemic curve is still on the rise. Dental professionals face unique challenges and work pressure due to the fear of the spread of disease while coming in close contact with the potential carriers. Aim: The aim is to assess the knowledge and preparedness level toward novel coronavirus diseases among the dental professionals of India. Methodology: Online survey was carried out from May 2020 to June 2020 on dental health care professionals through snowball sampling. A 24-item structured closed-ended online questionnaire was used. Statistical Analysis Used: Frequency distribution and proportions of the responses were analyzed using the SPSS version 21. Results: A total of 154 dental professionals participated in the study. Majority of the respondents (72.72%) were aware about the correct genomic structure of the virus and aptly identified the early neurological symptom of novel coronavirus disease. 85.71% of the respondents were appropriately informed about the infection control protocol to be followed. However, regarding the protection level to be used while dealing COVID patients, only 24.03% of respondents correctly identified it as Level III. Regarding the amendments required in dental practice and level of preparedness, only 50% of the dental health-care workers were aware of the sequence of donning of personal protective equipment. Conclusions: In the present study, dentists were found to have good knowledge toward novel coronavirus disease with optimum preparedness level for dental practice modification. Dental fraternity is further advised to follow the standard guidelines overcoming this pandemic.

6.
Journal of Communicable Diseases ; 2022:15-23, 2022.
Article in English | Scopus | ID: covidwho-1904117

ABSTRACT

Introduction: As new strains of SARCOV2 virus emerge across the world, it is imperative to investigate measures which restrict the movement of the general population such as social and travel restrictions by lockdowns to mitigate the effects of COVID-19. Thus, our paper helps in two ways: 1) Drastic measures like lockdown are essential but cannot be a feasible long-term intervention. Therefore, it is crucial to understand if the same unlock down can be reversed without compromising public health needs. Our paper provides evidence on the same;and 2) Our report also provides an insight into the trends of disease transmission during different phases of the un-lockdown. Methods: We examine the spread of pandemic during different phases of Un-lockdown (8th June to 31st October 2020). Since Rt calculation takes into consideration numerous factors, we use β, the transmission coefficient that governs the transition of population from Susceptible to Exposed pool, to examine the effect of public heaThelth interventions on disease spread. Results: The comparison of the distribution of fitted β values, thus calculated using SEIR model and GLM have been done and a Welch Two Sample t-test suggests that the GLM fitted β and SEIR β data sets are not significantly different from one another. Conclusion: We provide evidence that un-lockdown can be achieved without increasing the transmission of disease disproportionately. Thus, a phased wise approach to un-lockdown is encouraged. We also provide the rationale for using β over Rt values to specifically assess the effect of public health interventions designed to decrease exposure. Copyright (c) 2022: Author(s).

7.
Biofuels ; 2022.
Article in English | Scopus | ID: covidwho-1900962

ABSTRACT

Covid 19 is a highly infectious disease caused by SARS-CoV-2 that can spread from an infected person’s nose, mouth during coughing & sneezing. One of the warriors against Covid-19 is personal protection equipment (PPE), which is indispensable for everyone working closely with Covid-19 patients. The kits are made of different types of plastics and their disposal is going to be a serious menace, if not taken care of properly. The sustainable alternative to handle cast-off PPE kit is to convert them into pyrolysis oil using a thermochemical process. In the present paper, pyrolysis of PPE kit is done in a lab scale reactor to get the pyrolysis oil that has the potential to be used as alternate fuel in the neat or in blended form with conventional fuels. GC-MS of the obtained oil shows the presence of (C-7 to C-32) hydrocarbon fraction. FTIR analysis of the oil is also done for functional group composition. The results obtained also support the application of pyrolyisis oil as an alternate fuel. Physico-chemical characteristics of the pyrolysis oil sample are also comparable to the commercially available fuel with exception of viscosity as the fuel obtained has not been fractionated and has both light and heavy naphtha. © 2022 Informa UK Limited, trading as Taylor & Francis Group.

8.
Medical Science ; 26(122):8, 2022.
Article in English | Web of Science | ID: covidwho-1887480

ABSTRACT

COVID-19 (Coronavirus infectious disease 2019) denotes an ever changing and varied disease which has crippled the health care systems throughout the world. There have been studies conducted across the globe to establish the important factors for severity and mortality associated with COVID-19. We tried to study the effect of chronic obstructive pulmonary disease (COPD) on the severity as well as outcome of COVID-19. Material and methods: A total of 180 patients with COVID-19 were enrolled in this study and were then screened for history of COPD. There were 49 patients with history of COPD and 131 patients with no history of COPD. Inflammatory markers and HRCT scores were assessed for all the patients and they were followed up to study the outcome. Result: COPD was significantly associated HRCT Score, inflammatory markers and outcome. The mean HRCT Score for patients with COPD was more in COPD group (15.39 +/- 4.65) when compared with Non-COPD group (9.39 +/- 3.98). Mortality was also significantly higher in patients with COPD (67.3%) when compared to the patients without COPD (3.3%). Conclusion: We conclude that COPD is an important factor which has to be considered while treating the patients of COVID-19 especially in the rural India where lockdown restrictions and lack of knowledge have provided hinderance in achieving optimal follow up as there is increased severity and mortality associated with it.

9.
Topics in Antiviral Medicine ; 30(1 SUPPL):208, 2022.
Article in English | EMBASE | ID: covidwho-1880360

ABSTRACT

Background: Men who have sex with men (MSM) have been identified as one subgroup with continuous HCV transmission and as a target for HCV micro-elimination efforts. We assess newly acquired HCV among MSM in Germany since the introduction of directly-acting antiviral agents (DAAs). Methods: The German NoCo cohort consists of patients from six German HIV and hepatitis treatment sites providing care for more than 8000 HIV-positive MSM, and serving as primary care providers and HIV pre-exposure prophylaxis (PrEP) sites. Patients who were diagnosed with recently acquired HCV infection since 2014 were enrolled and are followed-up. Virologic data, HIV and HCV treatment data, risk factors and behavior as well as liver disease assessment is acquired regularly. Results: Between January 2014, and October 2021, 237 MSM with recently acquired HCV infection were included. A majority were Caucasian (95%), and mean age was 45.3 years (standard deviation, SD, 9.57). At HCV diagnosis, median ALT level was 224 U/L (interquartile range, IQR, 86-521), and median HCV viral load was 475,000 IU/mL (IQR 66,955-3,005,882). The most prevalent HCV genotype were 1a (58.7%), and 4d (16%). The risk factors for HCV acquisition were as follows: MSM: 92.4%, intravenous drug use: 2.95%, intranasal drug use: 0.8%, other: 0.4%, unknown: 7.2%. A subgroup of 21 (8.9%) MSM were not co-infected with HIV, of whom 15 (71.4%) were using PrEP. Anti-HCV treatment with DAAs was documented in 165 patients (71.7%), 18 (7.8%) had a spontaneous clearance, and in 47 patients (20.4%) treatment was not started. DAAs were initiated a median 6.6 months (IQR 4 to 9.3) after diagnosis;all treated patients achieved a sustained virologic response (SVR), or treatment was still ongoing (16%). Between 2014-2019 27-36 patients were diagnosed with recently acquired HCV annually. In relation to all HIV-positive MSM under care, the incidence was 0.33-0.39% per year with no significant change over time. In 2020, a decline in HCV incidence to 0.28% was observed. In 2021 HCV incidence dropped to 0.02%. In the same period, the number of patients seen in the centers remained stable, and routine HCV testing returned to pre-pandemic levels by the end of 2020. Conclusion: The German NoCo cohort demonstrated stable HCV incidence rates despite a broad use of DAAs. In 2021, however, micro-elimination goals were met, possibly due to behaviour changes related to the SARS-CoV-2 pandemic and associated containment measures.

10.
Journal of Long-Term Care ; 2021:167-176, 2021.
Article in English | Scopus | ID: covidwho-1876498

ABSTRACT

An important part of care home life is the support given to older residents by their families/friends through regular visiting. Social visits to residents by their families ceased in response to the COVID-19 pandemic and residents were confined to their rooms. This paper reports on how care home staff improvised to address this situation during the first wave of the pandemic. It focuses on steps taken to maintain communication between residents and families to support emotional well-being. We undertook in-depth café-style interviews with twenty-one staff to explore creative practices that they introduced. It was part of a wider Scottish study examining the effect of lockdown on families whose relative was living/dying in a care home (May–October, 2020). Findings reveal the enormous effort by care staff to maintain family connections and the rapid acclimatisation involved working with a number of different on-line platforms, the pulling together of staff from across the care home, and, the attention to emotional well-being of residents living and dying in the care home. Findings highlight the professionalism and commitment of the leadership and staff involved. Whilst some of the staff accounts need no further comment, we draw on some themes from the care home research literature to make sense of the findings in terms of what we might learn going forward. This in-depth qualitative study emphasises the importance of recognising, fostering and nurturing relational compassionate care within long-term care. There is however little evidence whether health and social care policies recognise the importance of this on-going relationship. © 2021 The Author(s).

11.
IEEE Visualization Conference (IEEE VIS) ; : 146-150, 2021.
Article in English | Web of Science | ID: covidwho-1868557

ABSTRACT

In order to effectively combat Air Pollution, it is necessary for the government and the community to work together. Easily comprehensible visualizations can play a major role in drawing public attention and spreading awareness about seemingly intangible air pollution. Considering the widespread usage of Android-based devices, in this paper, we propose an Augmented Reality based application called AiR, to help users to visualize pollutants in the air and to create an immersive user experience. It aims to interactively engage a wide variety of users and create awareness without overwhelming them with data. AiR visualizes 12 pollutants [PM10, PM2.5, NO, NO2, NOx, CO, SO2,O-3,NH3, C6H6, (CH3)C6H5 and (CH3)(2)C6H5] through unique models. We demonstrate our application on pollution data by CPCB from various weather stations across India collected over the initial lockdown period due to COVID-19 in India.

12.
21st International Conference on Intelligent Systems Design and Applications (ISDA) ; 418:933-943, 2021.
Article in English | Web of Science | ID: covidwho-1866602

ABSTRACT

As per World Health Organization, COVID-19 is causing even the most important health systems across the countries under considerable strain. The advanced recognition of COVID 19 will result into decreasing the stress of a lot of health systems. Much similar to the customary usage of Chest X-Rays for detecting different pathologies, COVID-19 can also be detected using X-Ray of patients that indicates a very critical function in the diagnosis of SARS Covid-19. With rampant growth in the area of Deep Learning (DL) as well as Machine Learning (ML), it is much easier to design the framework that can detect COVID-19 infection easily. This paper proposes deep learning-based detection process by incorporating the concept of Transfer Learning for the classification of this pandemic using X-ray images of chest. This non-invasive and early-prediction of the corona virus by observing the X-rays of chest can subsequently be utilized to estimate the expansion of COVID-19 in the patients. This study got a maximum of 97% classifiers' accuracy using ResNet based model. This method can be utilized to upscale the effectiveness of the screening process.

13.
Journal of Clinical and Experimental Hepatology ; 12:S43-S44, 2022.
Article in English | EMBASE | ID: covidwho-1859850

ABSTRACT

Background: COVID-19 has become a major health emergency worldwide. The characteristics and outcome of COVID-19 in patients with CLD remain unclear. Aims: CLD represents a major disease burden globally. Given this high burden, how different underlying liver conditions influence the outcome in patients with COVID-19 needs to be meticulously evaluated. So, we conducted this study to see the outcome of the patient and to look for predictors of severity and mortality in patients with CLD with COVID-19 infection. Methods: This was a single-center, observational study conducted at a tertiary care center. We recruit 50 consecutive patients of COVID-19 with CLD. Matched comparison group patients with CLD without COVID-19 collected retrospectively from historical data with 1:2 ratio using stratified sampling. Results: Mean age of the study population was 51 ± 12 years with the majority were male. Most patients (21/50) were presented with predominantly respiratory symptoms of which fever was the most common symptom (85%). Jaundice (70%) was the most common GI symptom. Twenty patients had ACLF. All patients with ACLF were having severe COVID-19 infection and succumb to multi-organ failure. Mortality was double in a patient with CLD with COVID-19 infection than historical control. Diabetes was the only comorbidity which was associated with severe infection. Patients in the severely ill subgroup had higher mortality, high creatinine, and raised D-dimer but lower lymphocytes count. (P <0.05). Multivariate logistic regression for severity showed that only D-dimer reached significance. CURB-65 score on admission and Child Turcotte Pugh score on admission correlates with mortality (P <0.05). Serum D-dimer level and reduced lymphocyte counts were associated with mortality on multivariate analysis. Conclusion: The presence of CLD in covid-19 patients was associated with a poor outcome. Raised D-dimer on admission can predict severe infection. Child-Pugh and CRUB65 scores were highly associated with non-survival among these patients.

14.
Journal of Clinical and Experimental Hepatology ; 12:S40-S41, 2022.
Article in English | EMBASE | ID: covidwho-1859849

ABSTRACT

Background: Coronavirus disease 2019 (COVID-19) is a respiratory system trophic disease. Liver involvement is emerging from recent data. Studies describing liver function test (LFT) abnormalities are sparse from our population. Aims: We studied LFT abnormalities in different categories of COVID-19 and its significance in relation to primary outcomes of in-hospital mortality. Methods: It was a retrospective study from a single center of a metropolitan city. All consecutive patients with proven COVID19 by reverse transcriptase-polymerase chain reaction from 23rd March 2020 till 31stOctober 2020 were enrolled. Of 3280 case records profiled, 1474 cases were included in the study. Clinical characteristics, biochemical parameters and outcomes were recorded. Results: Deranged LFTs were present in 681/1474 (46%) patients. Hepatocellular type of injury was most common (93%). Patients with deranged LFTs had more probability of developing severe disease (P<0.001) and mortality (P<0.001). Higher mean age (P<0.001), male gender (P<0.001), diabetes mellitus (P<0.001), chronic kidney disease (P<0.02) cirrhosis (P<0.001), lower oxygen saturation (SpO2) levels at admission (P<0.001), higher serum creatinine (P value<0.001), D-dimer levels (P<0.001) and positive radiological findings on Chest X-ray (P<0.001) were associated with deranged LFTs. Acute liver injury was seen in 65 (4.33%) cases on admission and 57(3.5%) cases during hospital stay. On admission, raised serum bilirubin, aspartate and alanine transaminases, international normalized ratio and low serum albumin were found to be significant. However, on multivariate analysis for predicting mortality, age, serum creatinine, and PaO2/FiO2 ratio only were found to be significant (P<0.001). Conclusion: In COVID-19, LFT abnormalities are common and multifactorial. As severity of disease progresses, derangement in LFT’s increase. However, it is not associated with in- hospital mortality.

16.
Journal of Pharmaceutical Sciences and Research ; 14(3):713-720, 2022.
Article in English | EMBASE | ID: covidwho-1848396

ABSTRACT

Salivary diagnostics is emerging as a propitious tool with a multitude of clinical applications. It has been into practice for centuries but has recently garnered scientific researchers and clinicians' interest due to its added benefits. In this review, we have emphasized the various components of saliva and its functionalities, an introduction to salivary diagnostics, and its application in the detection and prognosis of many ailments all around the globe. A segment about saliva's special uses in animals and its role in therapeutics and forensics has also been focused. With the continually evolving technologies and chemical equipment, several devices have been devised which are used in salivary diagnostics. The utilization of saliva and its biomarkers as a non-invasive diagnostic agent in several diseases, including malignancies, caries, novel coronavirus, psychological stress, diabetes, and much more, has been discussed.

17.
European Journal of Molecular and Clinical Medicine ; 9(3):2080-2089, 2022.
Article in English | EMBASE | ID: covidwho-1812735

ABSTRACT

A new disease SARS-COV -2 popularly known as COVID-19 had become global pandemic taking toll of many lives in short time. India is among the most severely affected countries with on-going COVID-19 pandemic. It is very crucial to determine the factors related to mortality in COVID-19 infected cases to reduce the further deaths. The aim of the study is to assess the determinants related with COVID-19 mortality. Objectives: 1.To study the socio demographic profile of deceased from COVID-19 infection. 2. Assessment of factors related to mortality from COVID-19 infection. Methodology: An observational retrospective study was conducted by telephonic interview of family members of all deceased provided in the line-list of deaths in the Meerut district, Uttar Pradesh, India on pre-designed pretested validated questionnaire during study period. The detailed information regarding progress of the disease and hospitalization was also obtained from the death summary of the hospital deaths and data collected was entered and analyzed in Epi info7.2.3.1 software. Result: The case fatality ratio is around 2%.Increasing age, male gender ,urban population, delay in investigation and hospitalization ,poor health seeking behaviour are the determining factors in increasing mortality. Breathlessness followed by fever, cough are the most common presenting symptoms. Diabetics with Hypertension are at very high risk as compared to isolated non communicable diseases. Conclusion: Though the COVID-19 disease is highly infectious but the mortality is not very high in first wave and vulnerable population needs more focus with proper planning and strategies. IEC needs to be promoted for early investigation and treatment.

18.
Journal of Clinical and Diagnostic Research ; 16(4):LC33-LC36, 2022.
Article in English | EMBASE | ID: covidwho-1791827

ABSTRACT

Introduction: Coronavirus Disease-19 (COVID-19) infection is associated with high rates of pulmonary and extrapulmonary complications that may continue to incur morbidity, disability and delayed mortality in survivors. These include hyperglycaemia, cardiac injury, acute ischaemic or haemorrhagic stroke, neurological deficits, acute kidney injury and liver injury. Aim: To describe symptoms and complications being faced by COVID-19 recovered patients, as well their socio-demographic profile and co-morbidities. Materials and Methods: This was a cross-sectional descriptive study conducted for the period of 12 months from April 2020-March 2021. Out of nearly 10,000 recovered COVID-19 patients, 1000 (calculated sample size) patients were selected randomly. The patients were categorised gender-wise (male and female) and locality-wise (urban and rural) and an attempt was made to find if any significant difference exists in the symptoms and complications based on above categorisation. The test used for this purpose was Chi-square test and Fisher’s-exact test. Results: Mean age of participants was 50.2±15.7 years and 43.8% had co-morbidities. Common complications included hyperglycaemia (n=28), acute kidney injury (n=8), acute liver injury (n=5), cardio-vascular accident and stroke (n=5), septicaemia (n=8), ischaemic heart disease (n=7), deep vein thrombosis (n=2), cytokine release syndrome (n=10) and post COVID-19 fibrosis (n=3). For septicaemia, a statistically significant difference (p<0.001) was found between urban and rural areas whereas no significant difference in post COVID-19 complications between males and females was observed. conclusion: The most common co-morbidity was diabetes mellitus and most common complication reported was hyperglycaemia.

19.
2022 International Conference for Advancement in Technology, ICONAT 2022 ; 2022.
Article in English | Scopus | ID: covidwho-1788722

ABSTRACT

With the increase in the cases of COVID-19, the necessity of improving testing and treatment is increasing rapidly. Many techniques are currently being used by the medical fraternity for detection of COVID-19 in a patient such as RT-PCR, Chest CT Scan Images, Chest X-Ray scans, etc. Among these techniques, a Chest CT scan has proven to be highly accurate for screening of the novel coronavirus. But a trained professional like a radiologist is needed to analyze the CT scan and determine whether the patient is positive or not. Due to the sudden spike in the number of infections, there is a shortage of such professionals. A machine learning based system can be highly effective in assisting the doctors if it can accurately predict COVID-19 from a chest CT scan. However, the number of chest CT scan images available are very less in order to build an accurate machine learning based predictive model. We present a generative model for data augmentation of COVID-19 positive and negative Chest CT images. We use Conditional DCGAN for generating nearly 1502 COVID-19 positive and 1510 negative images thus extending a publicly available dataset. We also build predictive models using pre-trained models like VGG and ResNet to detect COVID-19, achieving an accuracy upto 87.7%. We also apply the technique of knowledge distillation to build a lightweight and computationally cheap predictive model that has an accuracy of 86.2% and is nearly 11 times smaller than the best model available on the dataset. © 2022 IEEE.

20.
21st International Conference on Intelligent Systems Design and Applications, ISDA 2021 ; 418 LNNS:933-943, 2022.
Article in English | Scopus | ID: covidwho-1787720

ABSTRACT

As per World Health Organization, COVID-19 is causing even the most important health systems across the countries under considerable strain. The advanced recognition of COVID 19 will result into decreasing the stress of a lot of health systems. Much similar to the customary usage of Chest X-Rays for detecting different pathologies, COVID-19 can also be detected using X-Ray of patients that indicates a very critical function in the diagnosis of SARS Covid-19. With rampant growth in the area of Deep Learning (DL) as well as Machine Learning (ML), it is much easier to design the framework that can detect COVID-19 infection easily. This paper proposes deep learning-based detection process by incorporating the concept of Transfer Learning for the classification of this pandemic using X-ray images of chest. This non-invasive and early-prediction of the corona virus by observing the X-rays of chest can subsequently be utilized to estimate the expansion of COVID-19 in the patients. This study got a maximum of 97% classifiers’ accuracy using ResNet based model. This method can be utilized to upscale the effectiveness of the screening process. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

SELECTION OF CITATIONS
SEARCH DETAIL