PREVALENCE OF STROKE IN MUCORMYCOSIS PATIENTS WITH COVID-19 INFECTION IN INDIA

Background: During the second wave of COVID-19, India suffered from a catastrophic outburst of cases and rapid transmission of disease due to the highly infectious delta strain (B.1.617.2). Patients infected with this strain underwent prolonged hospitalisations, suffered from severe symptoms. A sudden surge of fungal infections, primarily Mucormycosis was observed. Methods: We conducted a case-control study to study various risk factors and form of intracranial involvement in cases of Mucormycosis. Results: Study included 121 patients in total;out of which 61 were Mucormycosis patients with prior COVID-19 infection. 30 out of 61 Mucormycosis patients had intracranial involvement with majority having stroke in the form of the either infarct (10 patients, 34%);or haemorrhage (3 patients, 10%) and thrombosis of artery involvement (8 patients, 29%). Other intracranial form of involvement was abscess (6 patients, 20%) and meningitis (2 patients, 7%). The most frequent type of infarcts were lacunar infarcts and the most common location of infarcts were middle cerebral artery (MCA) or anterior cerebral artery (ACA). Patients were treated with administration of Amphotericin B and Posaconazole. Telephonic follow-up was conducted after a time period of about 90 days and their health condition was recorded on basis of modified ranking scale (mRS). Out of the 30 Mucormycosis infection patients displaying the occurrence of stroke, 10 patients could not survive. q Conclusion: Intracranial Mucormycosis in COVID19 patients presenting with stroke were observed frequently and had mortality in about one-third cases.

STROKE THROMBOLYSIS DURING THE COVID PANDEMIC IN INDIA - A TALE OF TWO WAVES & LESSONS LEARNT

Background: The world was witness to a pandemic never experienced by this generation. The call to arms was answered by each branch of medicine, each fighting separate wars. The war, we as neurologists faced was the “Battle for the Vessels”. Health care workers are a precious resource in Low-Middle-Income-Countries. Hence, exposure to a covidpositive patient for a “full hour” during thrombolysis, isn't warranted. Hence Tenecteplase use which fits the bill “ideally” and “literally” was analysed in this study against Alteplase in strokes with covid-positivity. We analyse the factors which affect their action and the role covid had, in each scenario. Methods: This is an ambi-spective observational study of 37 patients in an apex tertiary-care centre in India. Routine stroke variables were assessed including follow-up imaging, functional outcomes at 3 months. The results were also analysed with the thrombolysis data from covidnegative individuals too in the same period. Results: Among the covid-positive patients 62.16% patients received tenecteplase while 37.83% received alteplase. Although the baseline characteristics were similar, the time-metrics for thrombolysis were significantly favourable in the tenecteplase arm. The median-hospital stay was shorter in the tenecteplase group as was the in-hospital mortality. On follow-up at 3 months, the median mRS-score was significantly favourable in the tenecteplase group. Conclusions: Thrombolysis during the pandemic has been a challenge in many ways especially in resource limited settings. This study shows that there needs to be a conscious and judicial transition towards tenecteplase during the pandemic, where healthcare workers are a precious resource too.

COVID-19 detection using hybrid deep learning model in chest x-rays images

The novel-corona-virus is presently accountable for 547,782 deaths worldwide. It was first observed in China in late 2019 and, the increase in number of its affected cases seriously disturbed almost every nation in terms of its economical, structural, educational growth. Furthermore, with the advancement of data-analytics and machine learning towards enhanced diagnostic tools for the infection, the growth rate in the affected patients has reduced considerably, thereby making it critical for AI researchers and experts from medical radiology to put more efforts in this side. In this regard, we present a controlled study which provides analysis of various potential possibilities in terms of detection models/algorithms for COVID-19 detection from radiology-based images like chest x-rays. We provide a rigorous comparison between the VGG16, VGG19, Residual Network, Dark-Net as the foundational network with the Single Shot MultiBox Detector (SSD) for predictions. With some preprocessing techniques specific to the task like CLAHE, this study shows the potential of the methodology relative to the existing techniques. The highest of all precision and recall were achieved with DenseNet201 + SSD512 as 93.01 and 94.98 respectively.

Covid-19 detection from chest X-Ray images using advanced deep learning techniques

Like the Covid-19 pandemic, smallpox virus infection broke out in the last century, wherein 500 million deaths were reported along with enormous economic loss. But unlike smallpox, the Covid-19 recorded a low exponential infection rate and mortality rate due to advancement in medical aid and diagnostics. Data analytics, machine learning, and automation techniques can help in early diagnostics and supporting treatments of many reported patients. This paper proposes a robust and efficient methodology for the early detection of COVID-19 from Chest X-Ray scans utilizing enhanced deep learning techniques. Our study suggests that using the Prediction and Deconvolutional Modules in combination with the SSD architecture can improve the performance of the model trained at this task. We used a publicly open CXR image dataset and implemented the detection model with task-specific pre-processing and near 80:20 split. This achieved a competitive specificity of 0.9474 and a sensibility/accuracy of 0.9597, which shall help better decision-making for various aspects of identification and treat the infection. © 2021 Tech Science Press. All rights reserved.

COVID-19 Detection: An Approach Using X-Ray Images and Deep Learning Techniques

In the recent history of human civilization, a pandemic affecting such an enormous population like COVID-19 was about 140 years ago-The Smallpox Worldwide Epidemic (1877–1977, Deaths-500 M). It can be easily inferred that the health management system over the globe in the nineteenth century was too underdeveloped than that of today, which also refers to the fact that the present epidemic must not be allowed to last much longer as the number of deaths is increasing nonlinearly (506 K, with 10.3 M affected). While the medical community around the globe is striving to find a permanent cure, it becomes evident responsibility of all professionals who can contribute in stabilizing the medical management systems of countries particularly underdeveloped/developing countries or those with highest rate of increase in COVID-19 cases like USA, Brazil. In this regard, this study introduces a fast, robust and practically effective method for detection of COVID-19 from chest x-ray images utilizing enhanced deep learning techniques. An object detection network is proposed to be trained with publicly existing datasets. In this model, SSD is used with ResNet101 as a base layer and some pre-processing, achieving a sensitivity of 0.9495 and a specificity of 0.9247. If practically implemented, this can prove very beneficial in aiding economies and health systems of the above-mentioned countries. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.