Accurate glaucoma diagnosis and management require understanding structural and functional measurements, and their complex relationship. In recent years, artificial intelligence (AI), particularly deep learning (DL), has shown great promise in analyzing fundus and optical coherence tomography images, as well as visual field data, for tasks such as diagnosis, progression analysis, knowledge discovery, data quality improvement, and even synthetic data generation. Advances in natural language processing (NLP) have also enabled the use of electronic health records, creating new opportunities for personalized treatment and outcome prediction. This chapter concisely reviews the literature on these AI applications, covering diagnosis (using structural and functional data), structure-function correlation analysis, longitudinal progression prediction, and NLP-enabled EHR data utilization. It also highlights challenges, including the need for larger, more diverse datasets, improved model explainability, and the diversity of glaucoma definitions.