ABSTRACT
A large quantity of potentially threatening COVID-19 false information is available online. In this article, machine learning approach is adopted to assess COVID-19 materials in online health advice adversaries, particularly those who oppose immunizations like (anti-vaccine). Pro-vaccination (pro-vaccine) group is emerging a more attentive conversation regarding COVID-19 above its corresponding portion, the anti-vaccine group. However, the anti-vaccine group presents a wide series of flavors of COVID-19-relatedtopics, andas a result, can demandto a wider cross-section of entities searching for COVID-19 assistance online, such as those who may be wary of receiving a COVID-19 vaccine as a condition of employment or those looking for alternative medications. Later, the anti-vaccine group appears to be better positioned than the pro-vaccine side to obtain complete support moving forward. This is important because if the COVID-19 vaccine is not widely used, the world will not be able to produce herd immunity, parting countries exposed to a COVID-19 comeback in the future. An automatic supervision machine learning model is provided that clarifies these results andcan be used to evaluate the efficacy of intervention efforts. Our method is adaptable and capable of addressing the crucial problem that social media platforms face when analyzing the vast amounts of online health misinformation. © 2022 IEEE
ABSTRACT
Introduction and Aim: The outbreak of Covid-19 pandemic since December 2019 has raised serious global health concern. Because of rapid human to human transmission and non-availability of clinically proven drugs or vaccines, this Covid-19 pandemic has created a great threat to mankind. Many naturally derived molecules are being investigated for the treatment of Covid-19. Ocimum americanum is one such significant medicinal plant possessing a variety of biological activities. Material(s) and Method(s): In the present study, seven phytochemicals were selected from O. americanum and were docked against SARS-CoV-2 spike protein which is an important site for virus to enter the host cell. Docking was performed using Autodock Vina and the ADME properties of all these seven ligands were predicted using the Swiss-ADME tool. The bioactivity score was also predicted using the Molinspiration tool. Besides the secondary metabolites, all these analyses were also performed for well-known antiviral drugs namely lopinavir and ritonavir. Result(s): The binding energy obtained from the docking studies of SARS-CoV-2 spike protein with Lopinavir, Ritonavir, Alpha-farnesene, Beta-farnesene, Eugenol, Linalool, Estragole, Limonene and 1,8-Cineole was found to be-5.2,-5.1,-4.7,-4.5,-4.3,-4.1,-4,-3.9 and-3.8 Kcal/Mol respectively. Swiss-ADME results also suggest that all the selected ligands follow the drug likeness properties and hence they could be taken for further drug discovery process. Conclusion(s): From the present in silico study, it can be concluded that secondary metabolites of O. americanum have potential inhibiting activity against spike protein of SARS-CoV-2. Isolation and efficacy studies in vitro may provide an insight into the drug discovery to fight Covid-19.Copyright © 2023, Indian Association of Biomedical Scientists. All rights reserved.
ABSTRACT
The COVID-19 pandemic has spread rapidly and significantly impacted most countries in the world. Providing an accurate forecast of COVID-19 at multiple scales would help inform public health decisions, but recent forecasting models are typically used at the state or country level. Furthermore, traditional mathematical models are limited by simplifying assumptions, while machine learning algorithms struggle to generalize to unseen trends. This motivates the need for hybrid machine learning models that integrate domain knowledge for accurate long-term prediction. We propose a three-layer, geographically informed ensemble, an extensive peer-learning framework, for predicting COVID-19 trends at the country, continent, and global levels. As the base layer, we develop a country-level predictor using a hybrid Graph Attention Network that incorporates a modified SIR model, adaptive loss function, and edge weights informed by mobility data. We aggregated 163 country GATs to train the continent and world MLP layers of the ensemble. Our results indicate that incorporating quantitatively accurate equations and real-world data to model inter-community interactions improves the performance of spatio-temporal machine learning algorithms. Additionally, we demonstrate that integrating geographic information (continent composition) improves the performance of the world predictor in our layered architecture. (PsycInfo Database Record (c) 2022 APA, all rights reserved)
ABSTRACT
Background: COVID-19, an acute viral respiratory illness, was first noted in 2019, soon turned into pandemic with considerable mortality. With the objective of studying effect of comorbidities on COVID-19 disease severity and to identify laboratory markers associated with severe COVID-19 disease, we did a retrospective observational study in a tertiary care centre. Aims and Objectives: The objectives of this study were as follows: 1. To study effect of comorbidity on COVID-19 disease severity and 2. to identify laboratory markers associated with severe COVID-19 infection and mortality. Materials and Methods: This is an retrospective observational study conducted at SDMCMS&H, Dharwad from July 2020 to September 2020. A total of 402 cases who fall in the age group of 18 years and above were collected from medical record department. Statistical analysis used: The data were recorded in the Microsoft Excel sheet and analysis is done using Chi-square analysis and Cox linear regression method. Results: There were 402 patients whose data were collected. Out of 402 patients, 64 patients (15.92%) were in the age group of 18-39 years, 183 patients (45.52%) seen were in the age group of 40-60 years, 155 patients (38.56%) above 60 years, and consisting 291 male patients (72.39%) and 111 female patients (27.9%). Most common comorbidities seen were diabetes mellitus in 194 patients (48.26%) and hypertension in 182 patients (45.27%), followed by chronic kidney disease in 32 patients (7.96%) and ischemic heart disease in 24 patients (5.97%). Out 402 patients, 141 patients (35.07%) were on supplemental oxygen, which included 68 patients (48.23%) on low flow oxygen by face mask, seven patients (4.96%) were on non-rebreathing mask, 3 (2.13%) patients required NIV, and 63 patients (44.68%) required intubation and mechanical ventilation. It was found that uncontrolled diabetes rather than just presence of diabetes had significant impact on mortality with P=-0.0001 (95% CI OR 1.5-4.38). Patients with increased laboratory markers of inflammation such as Ferritin (95% CI OR 1.84-6.81) and LDH (95% CI OR 1.86-31.26) had strong association with mortality. The presence of thrombocytopenia showed significant association with mortality (95% CI OR 1.03-3.63). Conclusion: The presence of preceding uncontrolled hyperglycemia has significant effect on mortality. A state of hyperinflammation is directly associated with poor outcome.
ABSTRACT
Introduction: A cluster of pneumonia cases were recognised at the end of the year 2019, and later designated as Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2). It was declared as pandemic in early 2020. Coronavirus Disease 2019 (COVID-19) caused considerable morbidity and mortality. Further, it was discovered that presence of co-morbidities like diabetes mellitus, ischaemic heart disease and appearance of cytokine storm caused increased mortality. Aim(s): To identify co-morbidities and laboratory parameters associated with prolonged hospitalisation in COVID-19 disease. Material(s) and Method(s): This retrospective study was conducted in Department of General Medicine at SDM College of Medical Sciences and Hospital, Shri Dharmasthala Manjunatheshwara University, Dharwad, Karnataka, India (tertiary care hospital). Data between 1st July 2020 to 30th September 2020 was collected, and analysis and interpretation was done from November 2020 to March 2021 from data obtained from medical records. Data of 402 participants was analysed for baseline characteristics like demographic distribution (age and gender), presence of co-morbidities like diabetes mellitus, hypertension, ischaemic heart disease. Patients were divided as per level of oxygen requirements, duration of hospitalisation and usage of remdesivir or steroid or both. Laboratory parameters studied were complete blood count, platelet count, serum sodium, parameters of hyperinflammation like C-reactive Protein (CRP), Lactate dehydrogenase (LDH), ferritin. Markers of COVID-19 associated with high mortality like Neutrophil to Lymphocyte Ratio (NLR) and D-dimer were also taken. Mean hospital stay was associated with all the parameters. Data was analysed by one way Analysis of Variance (ANOVA) and Independent t-test. Result(s): Maximum patients seen were in the age group of 40-60 years (45.52%). Common co-morbidities observed were diabetes mellitus (48.26%) and hypertension (45.27%). Presence of co-morbidities like diabetes mellitus (p-value=0.0171), hypertension (p-value =0.0238), ischaemic heart disease (p-value=0.0024) was associated with prolonged hospitalisation. Among laboratory markers higher level of parameters of inflammation like NLR >2 (p-value=0.0183), CRP >6 mg/L (p-value=0.004), ferritin >300 ng/mL (p-value=0.05) and indicators of hypercoagulable state {D-dimer >500 ng/mL (p-value=0.0014)} were associated with significantly prolonged stay. patient who received both remdesivir and steroids stayed longer compared to either remdesivir alone or only steroids (p-value=0.0001). Conclusion(s): State of hyperinflammation and presence of co-morbidity especially uncontrolled diabetes mellitus and usage of steroids were associated with prolonged hospitalisation. Periodic assessment of these patients until recovery may help reducing mortality and morbidity. Copyright © 2022 Journal of Clinical and Diagnostic Research. All rights reserved.
ABSTRACT
Background: COVID-19, an acute viral respiratory illness, was first noted in 2019, soon turned into pandemic with considerable mortality. With the objective of studying effect of comorbidities on COVID-19 disease severity and to identify laboratory markers associated with severe COVID-19 disease, we did a retrospective observational study in a tertiary care centre. Aims and Objectives: The objectives of this study were as follows: 1. To study effect of comorbidity on COVID-19 disease severity and 2. to identify laboratory markers associated with severe COVID-19 infection and mortality. Materials and Methods: This is an retrospective observational study conducted at SDMCMS&H, Dharwad from July 2020 to September 2020. A total of 402 cases who fall in the age group of 18 years and above were collected from medical record department. Statistical analysis used: The data were recorded in the Microsoft Excel sheet and analysis is done using Chi-square analysis and Cox linear regression method. Results: There were 402 patients whose data were collected. Out of 402 patients, 64 patients (15.92%) were in the age group of 18–39 years, 183 patients (45.52%) seen were in the age group of 40–60 years, 155 patients (38.56%) above 60 years, and consisting 291 male patients (72.39%) and 111 female patients (27.9%). Most common comorbidities seen were diabetes mellitus in 194 patients (48.26%) and hypertension in 182 patients (45.27%), followed by chronic kidney disease in 32 patients (7.96%) and ischemic heart disease in 24 patients (5.97%). Out 402 patients, 141 patients (35.07%) were on supplemental oxygen, which included 68 patients (48.23%) on low flow oxygen by face mask, seven patients (4.96%) were on non-rebreathing mask, 3 (2.13%) patients required NIV, and 63 patients (44.68%) required intubation and mechanical ventilation. It was found that uncontrolled diabetes rather than just presence of diabetes had significant impact on mortality with P=−0.0001 (95% CI OR 1.5–4.38). Patients with increased laboratory markers of inflammation such as Ferritin (95% CI OR 1.84–6.81) and LDH (95% CI OR 1.86–31.26) had strong association with mortality. The presence of thrombocytopenia showed significant association with mortality (95% CI OR 1.03–3.63). Conclusion: The presence of preceding uncontrolled hyperglycemia has significant effect on mortality. A state of hyperinflammation is directly associated with poor outcome. [ FROM AUTHOR] Copyright of Asian Journal of Medical Sciences is the property of Manipal Colleges of Medical Sciences and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)
ABSTRACT
Automatic recognition of lung system is use to identify normal and covid infected lungs from chest X-ray images of the people. In the year 2020, the coronavirus forcefully pushed the entire world into a freakish situation, the foremost challenge is to diagnosis the coronavirus. We have got standard diagnosis test called PCR test which is complex and costlier to check the patient's sample at initial stage. Keeping this in mind, we developed a work to recognize the chest X-ray image automatically and label it as Covid or normal lungs. For this work, we collected the dataset from open-source data repository and then pre-process each X-ray images from each category such as covid X-ray images and non-covid X-ray images using various techniques such as filtering, edge detection, segmentation, etc., and then the pre-processed X-ray images are trained using CNN-Resnet18 network. Using PyTorch python package, the resnet-18 network layer is created which gives more accuracy than any other algorithm. From the acquired knowledge the model is correctly classifies the testing X-ray images. Then the performance of the model is calculated and analyzed with various algorithms and hence gives that the resnet-18 network improves our model performance in terms of specificity and sensitivity with more than 90%.