Artificial Intelligence in Neovascular Age-Related Macular Degeneration.

Abstract

The integration of artificial intelligence (AI) into the management of neovascular age-related macular degeneration (nAMD) presents a transformative opportunity in ophthalmology. In particular, deep learning (DL) models have shown remarkable accuracy in detecting nAMD, predicting disease progression and forecasting treatment outcomes. This review provides a comprehensive analysis of current AI applications in nAMD, focusing on the performance of these models in diagnostic tasks, including classification, object detection, and segmentation, as well as their potential to outperform human experts in specific domains. The review further explores how AI-driven predictive models can personalize treatment strategies by forecasting individual responses to therapies, such as anti-VEGF, and predicting the conversion from intermediate AMD to nAMD. Despite these promising developments, significant challenges remain, including the need for extensive datasets, seamless integration into clinical workflows, and ensuring the generalizability of AI predictions across diverse populations. Continued validation and the development of user-friendly AI tools are crucial for broader adoption and improved patient outcomes. In conclusion, identifying effective pathways to overcome these challenges will be essential as the field continues to evolve.