Performance of OCT-Based Artificial Intelligence Models for Detecting and Predicting Glaucoma Progression: A Systematic Review

Background/Objectives: Glaucoma is a leading cause of irreversible blindness globally and must be detected early to preserve vision. Standard methods, such as automated perimetry and optical coherence tomography (OCT), are limited in their ability to detect early changes. Therefore, this systematic review evaluates the diagnostic and predictive performance of artificial intelligence (AI)-driven OCT-based models, including those based on deep learning, machine learning, and transformer architectures, and contextualizes their performance against the recognized limitations of standard automated perimetry and conventional OCT trend analysis. Methods: The PubMed, Ovid, and Google Scholar databases were comprehensively searched to identify relevant published research in English. Screening of observational, cohort, prospective, retrospective and diagnostic accuracy studies, as well as clinical trials, identified 13 studies. Their key outcomes, including sensitivity, specificity, and area under the curve (AUC), were extracted for synthesis. Results: AI-driven OCT-based models generally reported high diagnostic performance, with mean sensitivities and specificities exceeding 80%, as well as AUC values generally above 0.85. AI-driven OCT-based models were reported to detect glaucoma progression as early as 9 months before standard methods. Conclusions: The findings suggest that AI-driven OCT-based models may improve glaucoma detection by identifying subtle structural and functional changes earlier, which may help inform earlier intervention decisions. However, the majority of included studies relied on internal validation only, and prospective multicenter studies with external validation are required before AI-driven OCT-based models can be reliably implemented in routine glaucoma care.