The global community is presently undergoing a pandemic, specifically the COVID-19 pandemic, which has emerged as a consequence of the identification of a novel coronavirus disease in Wuhan, China in 2019. Consequently, a considerable number of over 200 countries and dependent territories have witnessed an approximate total of 768 million infections, leading to a significant loss of 69.5 million lives. As a result, the global economy, daily life, and individuals' health will experience adverse consequences. Hence, the timely detection of COVID-19 is imperative to mitigate its transmission among individuals and reduce the associated fatality rate. The efficiency and timeliness of COVID-19 case detection can be enhanced through the utilization of computer-aided diagnosis (CAD) techniques in medical imaging, particularly in the context of chest X-rays. This is due to the advantageous characteristic of low radiation exposure offered by CAD, as compared to computed tomography (CT) methods. The present study involves the development of an automated diagnostic methodology utilizing a convolutional neural network (CNN) to forecast the presence of COVID-19 based on chest X-ray images. Our contribution is comprised of three key elements: Initially, the X-ray images undergo data pre-processing techniques, such as image resizing, to adequately prepare them for further analysis. Subsequently, a CNN model is utilized to generate predictions using the aforementioned pre-processed images, striking a balance between the intricacy of the model and computational efficiency. Ultimately, the performance of the model is assessed by employing established evaluation metrics and juxtaposing them against state-of-the-art methodologies.