Artificial intelligence (AI) has progressed from splitting innovation to real world applications as deep learning methods have advanced. AI is used in illness diagnosis and therapy, care coordination, medication research and development, and precision medicine. Collaborative efforts across disciplines will be essential for developing new AI algorithms for medical applications. One suitable strategy is to utilise machine learning to help clinicians diagnose chest X-ray images. In this study, we analyze the important methodology for developing an AI model and selection of appropriate machine learning techniques, locating openly available datasets of chest X-ray images (JPEG). Training datasets, deep learning models, and analysis methodologies have been tested using freely available sets of chest X-ray images. We used chest X-ray pictures from the Chest X-Ray Images (Pneumonia) collection for our research. This dataset is connected to the work on image-based deep learning for identifying medical diagnosis and curable disorders. This dataset comprises 5,856 chest X-ray pictures classified as Normal and Pneumonia. The Pneumonia category contains graphics of pneumonia that have been identified as either bacterial or viral. Further, we examine the best Convolutional Neural Network (CNN) model for the task that has been evaluated using a test set of chest x-ray images. Several measures are used to assess the model’s performance such as accuracy, precision, recall, F1 score, and AUC score.