This research is focused on developing an automated system for forecasting COVID-19 cases by leveraging pre-trained convolutional neural network (CNN) models and chest X-ray images. The primary objective is to create a model with significant clinical potential for early diagnosis of the disease, achieved by integrating advancements in computer vision and medical image analysis. The research aims to evaluate a range of convolutional neural network architectures for automated COVID-19 detection using X-ray images, and to assess the efficacy of these models through expert diagnosis facilitated by deep learning techniques. Given the constraints posed by a limited dataset, the study identifies InceptionNetV3 as the most suitable model due to its superior performance metrics. Specifically, the InceptionNetV3 model demonstrated an impressive accuracy of 98.63% when data augmentation techniques were applied. This high accuracy underscores the model's robustness in handling the challenges associated with limited data. Without data augmentation, however, the models tend to overfit, a common issue when training on small datasets. To address this, the proposed deep learning model has been meticulously trained using X-ray images from patients diagnosed with COVID-19, as well as images from healthy individuals and those with pneumonia. This approach is designed to enhance the model’s ability to distinguish between different conditions and improve diagnostic accuracy. The overarching goal of this research is to assist healthcare professionals by providing a reliable tool for early COVID-19 detection, thereby supporting better clinical decision-making. Additionally, the study outlines the procedures involved in utilizing transfer learning techniques for the automated detection of COVID-19, contributing to the broader field of medical imaging and deep learning.