This study investigates the use of deep learning models, specifically VGG-16 and LSTM, to diagnose COVID-19 from chest X-ray (CXR) images. The models were trained on a dataset of CXR images from normal, pneumonia, and COVID-19 patients. The results demonstrate high accuracy in classifying these three categories, highlighting the potential of this approach for rapid and efficient COVID-19 screening, especially in resource-constrained settings.