Evaluation of commercial RT-PCR kits for pooled clinical specimens in COVID-19 patients

Background:There are more than 350 RT-PCR COVID-19 testing kits commercially available but these kits has not been evaluated for pooled sample testing. Thus, this study was planned to compare and evaluate seven commercially availa- ble kits for pooled samples testing. Methods:Diagnostic accuracy of (1) TRUPCR SARS-CoV-2 Kit (Black Bio, India) (2) TaqPath RT-PCR COVID-19 Kit (Thermo Fisher, USA) (3) Allplex 2019-nCOV Assay (See gene, Korea), (4) Patho detect COVID-19 PCR kit (My Lab, India) (5) LabGun COVID-19 RT-PCR Kit (Lab Genomics, Korea) (6) Fosun COVID-19 RT-PCR detection kit (Fosun Ltd, China) (7) Real time Fluorescent RT PCR kit for SARS CoV – 2 (BGI, china) was evaluated on pre characterised 40 positive and 10 nega- tive COVID-19 sample pools. Results:All seven kits detected all sample pool with low Ct value (<30). While testing weak positive pooled samples with high Ct value (>30);TRUPCR Kit, TaqPath Kit, Allplex Assay and BGI RT PCR kit showed 100% sensitivity, specificity and accuracy. However;Fosun kit, LabGun Kit and Patho detect kit could detect only 90%, 85% and 75% of weak positive samples respectively. [Formula presented] Conclusions:We conclude that all seven commercially available RT-PCR kits included in this study can be used for routine molecular diagnosis of COVID-19. While perform- ing pooled sample testing it might be advisable to use those kits that performed best regarding the positive iden- tification in samples pool i.e. TRUPCR SARS-CoV-2 Kit, TaqPath RT-PCR COVID-19 Kit, Allplex 2019-nCOV Assay and BGI Real time RT PCR kit for detecting SARS CoV – 2.

Deep Learning Approach for Analyzing the COVID-19 Chest X-Rays.

PURPOSE: The purpose of this study is to analyze the utility of Convolutional Neural Network (CNN) in medical image analysis. In this study, deep learning (DL) models were used to classify the X-ray into COVID, viral pneumonia, and normal categories. MATERIALS AND METHODS: In this study, we have compared the results 9 layers CNN model (9 LC) developed by us with 2 transfer learning models (Visual Geometry Group) 16 and VGG19. Two different datasets used in this study were obtained from the Kaggle database and the Radiodiagnosis department of our institution. RESULTS: In our study, VGG16 yields the highest accuracy among all three models for different datasets as the Kaggle dataset-94.96% and the department of Radiodiagnosis dataset 85.71%. Although, the precision was found better while using 9 LC and VGG19 for both datasets. CONCLUSIONS: DL can help the radiologists in the speedy prediction of diseases and detecting minor features of the disease which may be missed by the human eye. In the present study, we have used three models, i.e.,, CNN with 9 LCs, VGG16, and VGG19 transfer learning models for the classification of X-ray images with good accuracy and precision. DL may play a key role in analyzing the medical image dataset.