Clinical Profile, Immunosuppressive Managment and Outcome in Adult Renal Allograft Recipients with Covid-19 Infection: A Case Series from Single Centre in Bangladesh

Introduction: The Novel Coronavirus disease 2019 (COVID-19), a respiratory infection has become a global concern. Given to the extent of the COVID-19 pandemic, it has been explored that Renal Allograft Recipients are considered high risk group for unfavourable outcome due to multiple comorbidities, long term immunosuppressive medications and residual CKD. This case series demonstrates clinical characteristics and outcome of COVID-19 infection in Renal Allograft Recipients. Method(s): Here we present 20 adult Renal Allograft Recipients admitted with moderate to severe symptom and RT PCR confirmed COVID-19 infection at united hospital limited from August 2020 to December 2021. We assessed demographic characteristics, comorbidities, clinical and laboratory parameters, radiological findings, immunosuppressive management and outcome. Result(s): Among all,15 patients were male with median age 55 years (range,34-75years). Mean time interval between renal transplantation were 90 months (24-132 months). Common comorbidities were hypertension (n=19), DM (n=18), lung diseases (n=13), IHD (n=9). Fever (100%) was most common symptom followed by cough(80%), sore throat(75%), and diarrhoea(60%). Nine (45%) patients who presented with dyspnoea during admission further progressed to poor outcome. During admission mean baseline creatinine was 1.51mg/dl(0.66-3.1 mg/dl), 15 patients had lymphopenia and 11 patients had higher inflammatory markers like high ferritin level, CRP, procalcitonin, LDH and D-dimer. Total 15 patients had abnormal HRCT findings and most common finding was unilateral or bilateral Ground glass opacity followed by consolidation, pleural effusion and interlobular septal thickening with mean TSS scoring being 8 (range 4-16). All patients were on triple immunosuppressive regimen (antimetabolites, CNI, low dose steroid).After admission antimetabolites were withdrawn in all patients, CNI were continued in 10 patients, 50% reduction in 2 patients, complete cessation of CNI in 8 patients and low dose steroids were switched to dexamethasone 6mg/ day. Other treatments included antiviral (Favipiravir, Remdisivir), antibiotics, LMWH followed by Rivaroxaban. Total 3 patients received Tocilizumab and Convalescent plasma was administered in 2 patients. Among all, 18 patients received different form of oxygen therapy, 9 patients were transferred to ICU, 7 patients required mechanical ventilation and 4 patients developed ARDS. 8 patients had other bacterial or fungal coinfection. six patients developed AKI and 2 of them needed Renal replacement therapy (RRT). Total 4 patients of AKI and 1 patient who required RRT finally expired. Total 6 patients died and after a median 18 days of admission. Conclusion(s): In this case series we describe 30% mortality rate. Older age, severe symptom specially dyspnoea during presentation, multiple comorbidities, high inflammatory markers, high baseline creatinine developing AKI, high TSS score at HRCT and requirement of mechanical ventilation were associated with high risk of death. No conflict of interestCopyright © 2023

ADPT: An Automated Disease Prognosis Tool Towards Classifying Medical Disease Using Hybrid Architecture of Deep Learning Paradigm

The Covid 19 beta coronavirus, commonly known as the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), is currently one of the most significant RNA-type viruses in human health. However, more such epidemics occurred beforehand because they were not limited. Much research has recently been carried out on classifying the disease. Still, no automated diagnostic tools have been developed to identify multiple diseases using X-ray, Computed Tomography (CT) scan, or Magnetic Resonance Imaging (MRI) images. In this research, several Tate-of-the-art techniques have been applied to the Chest-Xray, CT scan, and MRI segmented images' datasets and trained them simultaneously. Deep learning models based on VGG16, VGG19, InceptionV3, ResNet50, Capsule Network, DenseNet architecture, Exception and Optimized Convolutional Neural Network (Optimized CNN) were applied to the detecting of Covid-19 contaminated situation, Alzheimer's disease, and Lung infected tissues. Due to efforts taken to reduce model losses and overfitting, the models' performances have improved in terms of accuracy. With the use of image augmentation techniques like flip-up, flip-down, flip-left, flip-right, etc., the size of the training dataset was further increased. In addition, we have proposed a mobile application by integrating a deep learning model to make the diagnosis faster. Eventually, we applied the Image fusion technique to analyze the medical images by extracting meaningful insights from the multimodal imaging modalities. © 2022 IEEE.

An Efficient K-Means Clustering Algorithm for Analysing COVID-19

COVID-19 hits the world like a storm by arising pandemic situations for most of the countries around the world. The whole world is trying to overcome this pandemic situation. A better health care quality may help a country to tackle the pandemic. Making clusters of countries with similar types of health care quality provides an insight into the quality of health care in different countries. In the area of machine learning and data science, the K-means clustering algorithm is typically used to create clusters based on similarity. In this paper, we propose an efficient K-means clustering method that determines the initial centroids of the clusters efficiently. Based on this proposed method, we have determined health care quality clusters of countries utilizing the COVID-19 datasets. Experimental results show that our proposed method reduces the number of iterations and execution time to analyze COVID-19 while comparing with the traditional k-means clustering algorithm. © 2021, The Author(s), under exclusive license to Springer Nature Switzerland AG.