RESUMO
The coronavirus COVID-19 pandemic is today's major public health crisis, we have faced since the Second World War. The pandemic is spreading around the globe like a wave, and according to the World Health Organization's recent report, the number of confirmed cases and deaths are rising rapidly. COVID-19 pandemic has created severe social, economic, and political crises, which in turn will leave long-lasting scars. One of the countermeasures against controlling coronavirus outbreak is specific, accurate, reliable, and rapid detection technique to identify infected patients. The availability and affordability of RT-PCR kits remains a major bottleneck in many countries, while handling COVID-19 outbreak effectively. Recent findings indicate that chest radiography anomalies can characterize patients with COVID-19 infection. In this study, Corona-Nidaan, a lightweight deep convolutional neural network (DCNN), is proposed to detect COVID-19, Pneumonia, and Normal cases from chest X-ray image analysis; without any human intervention. We introduce a simple minority class oversampling method for dealing with imbalanced dataset problem. The impact of transfer learning with pre-trained CNNs on chest X-ray based COVID-19 infection detection is also investigated. Experimental analysis shows that Corona-Nidaan model outperforms prior works and other pre-trained CNN based models. The model achieved 95% accuracy for three-class classification with 94% precision and recall for COVID-19 cases. While studying the performance of various pre-trained models, it is also found that VGG19 outperforms other pre-trained CNN models by achieving 93% accuracy with 87% recall and 93% precision for COVID-19 infection detection. The model is evaluated by screening the COVID-19 infected Indian Patient chest X-ray dataset with good accuracy.
RESUMO
Background: 'Time is brain' goes the adage. Rapid and precise management of stroke is of the utmost essence. The modified National Institutes of Health Stroke Scale (mNIHSS) and the modified Rankin Scale (mRS) predict stroke severity and functional disability outcomes. However, the mRS can be administered more rapidly than the mNIHSS and therefore might be better to assess patient outcomes. Hence, the aim of this study was to assess the correlation of stroke severity on admission and functional disability outcomes on the day of discharge or on the 8th day of hospitalization. Materials and Methods: This was an observational, cross-sectional study with a sample size of 61 participants. The mNIHSS score was calculated on admission for patients with clinical features suggestive of stroke and mRS was calculated on the 8th day of hospitalization or on discharge. Evaluation of the association between continuous variables was done using Spearman's correlation analysis. Results: Correlation between mNIHSS and mRS was positive and statistically significant (rho = 0.866, 95% CI [0.751, 0.925]. For each point increase in the mNIHSS, the odds of having higher mRS scores are 153% more than the odds of having lower mRS scores (aOR = 2.534, 95% CI [1.904, 3.560]). Conclusion: Our study concluded that mRS can be reliably used to predict the functional outcomes for patients with stroke in circumstances where the mNIHSS may prove to be lengthy. Thus, where 'time is brain', the mRS can be used with a similar power to predict the outcome.
RESUMO
Various inflammatory markers have been used to show an association between welding and respiratory tract disorders due to inhalation of fumes. We hereby present a case of 19-year-old male, welder by occupation who presented with upper respiratory tract infection and was documented to have persistent moderate eosinophilia on serial Complete Blood Count (CBC) examination. This was also confirmed by bone marrow examination which was suggestive of increased eosinophilic precursors. Eosinophils are an inflammatory marker and are increased most commonly in respiratory tract of welders due to inhalation of metal fumes. Treatment with steroid is gratifying and provides short term symptomatic relief. Avoidance of metal fumes and/or change of job is the long term preventive measure. Welding occupation, as a risk factor, should be considered for causation of persistent respiratory tract inflammation with eosinophilia.
RESUMO
INTRODUCTION: Vitamin B12 deficiency is mainly diagnosed in symptomatic patients. However, the deficiency may also be prevalent in asymptomatic patients. Our aim was to study the prevalence of Vit B12 deficiency in IT professionals (Information Technology Professionals from Software industry) who presented for routine health screening and to correlate the deficiency to various parameters. MATERIALS AND METHODS: This was single centre, observational study comprising of 84 IT professionals. The data was collected in structured format. The study was designed to identify prevalence of Vit B12 deficiency and correlate to other factors such as type of diet, income level & regular use of medication (such as Antacid & Metformin). RESULTS: Total 28 individuals were found to be deficient (33.34%). Prevalence of Vit B12 deficiency amongst Vegetarian and non vegetarian diet adhering subjects was 47.5% and 20.45% respectively. B12 deficiency was also prevalent in high income age group. Further chronic intake of PPI (Proton pump inhibitor) and Metformin was associated with prevalence of 37.5% and 33.34% in the present study. CONCLUSION: During health screening of IT Professionals, significant prevalence of Vit B12 deficiency was noted across all income groups & non vegetarian diet consuming subjects also. There is significant correlation between Vit B12 deficiency with chronic use of PPI and Metformin.