The Role of Artificial Intelligence in Imaging-Based Diagnosis of Retinal Dystrophy and Evaluation of Gene Therapy Efficacy

<b>Introduction:</b> Inherited retinal dystrophies (IRDs) are genetically determined conditions leading to progressive vision loss. Developments in gene therapy are creating new treatment options for IRD, but require precise imaging diagnosis and monitoring. According to recent studies, artificial intelligence, especially deep neural networks, could become an important tool for analyzing imaging data. <b>Material and Methods:</b> A systematic literature review was conducted in accordance with PRISMA guidelines, using PubMed, Scopus, and Web of Science databases to identify publications from 2015 to 2025 on the application of artificial intelligence in diagnosing inherited retinal dystrophies and monitoring the effects of gene therapy. The included articles passed a two-stage selection process and met the methodological quality criteria. <b>Results:</b> Among all the included studies it can be noticed that the use of artificial intelligence in diagnostics and therapy of IRDs is rather effective. The most common method was deep learning with its subtype convolutional neural networks (CNNs). However, there is still a place for improvement due to various limitations occurring in the studies. <b>Conclusions:</b> The review points to the growing potential of AI models in optimizing the diagnostic and therapeutic pathway in IRDs, while noting current limitations such as low data availability, the need for clinical validation, and the interpretability of the models. AI may play a key role in personalized ophthalmic medicine in the near future, supporting both clinical decisions and interventional study design.