Due to the rapid spread of coronavirus 2019 (Covid 19) in the present situation ,early detection of covid 19 is very important. As per WHO [1] as of 5:26pm CEST, 5 August 2022, there have been 579,092,623 confirmed cases of COVID-19, including 6,407,556 deaths, reported globally. Lot of works have been reported to investigate covid19 using Deep learning algorithm over chest X-ray(CXR) images but as per our knowledge all have taken image data only as input to classify .In our work we have processed CNN model which can take CXR images along with corresponding the metadata(non imaging data) available with the dataset to classify Covid 19.CNN model based on Resnet 50,Dense net 121,Mobile Net,VGG-16,Inception-V3 and custom CNN have been developed to accept the multimodal data,i.e metadata along with CXR image.All the mentioned CNN have been used as feature extractor of CXR image and extracted feature have been fused with the features extracted from metadata and Article Title passed through the classifier for final classification.Some state of art Deep learning models have been run to classify the covid 19 on the same data set and compared with our best model .Experiments have been done in two phases.In the 1st phase we used CNN models on CXR image only and in the 2nd phase we ran all modified CNN models over the same CXR images with their matadata.The experimental results shows that the output of 2nd phase out performs the output of 1st phase.After that we compared our best model with other state of art models.Modified custom CNN model provides best results of 99.07 % overall accuracy