Chronic Obstructive Pulmonary Disease (COPD) is a global public health concern, encompassing a spectrum of respiratory conditions, including Pneumonia and Middle East Respiratory Syndrome Coronavirus (MERS-CoV). Early and accurate detection of COPD-related diseases is crucial for effective patient management and improved outcomes. This research presents a novel approach to detect and classify COPD diseases, specifically Pneumonia and MERS-CoV, by leveraging advanced machine learning techniques. We investigate the application of machine learning for the early detection and classification of Chronic Obstructive Pulmonary Disease (COPD)-related diseases, including pneumonia and MERS-CoV. A multifaceted dataset encompassing medical images, clinical data, and patient histories is leveraged to train and validate machine learning models. Convolutional Neural Networks (CNNs) are employed for image analysis, while traditional machine learning algorithms handle clinical data. Feature engineering techniques are used to optimize data informativeness. This approach holds promise for improving diagnostic accuracy, enabling timely interventions, and ultimately contributing to better outcomes in COPD management. Keywords: Convolutional neural networks , Machine learning, Training Data , Transfer Learning