Rapid advancements in artificial intelligence (AI) have revolutionized biomarker identification for pulmonary diseases, leading to significant improvements in diagnostic accuracy and treatment strategies. This review aims to comprehensively analyze the latest AI techniques used in identifying biomarkers for pulmonary conditions, such as chronic obstructive pulmonary disease (COPD), asthma, and lung cancer. By examining recent studies that leverage machine learning algorithms, deep learning models, and data integration methods, we highlight both the progress made and the challenges faced in this field. Key advancements include the application of convolutional neural networks (CNNs) for image-based biomarker discovery and the use of natural language processing (NLP) for extracting relevant clinical data. While significant advances have been achieved in this field, researchers continue to encounter fundamental challenges, particularly in ensuring data integrity, developing generalizable models, and establishing robust clinical validation protocols. This review underscores the transformative potential of AI in biomarker identification for pulmonary diseases and calls for further research to address these challenges and enhance clinical implementation.