Artificial Intelligence in Neuro-Ophthalmology for Optic Disc Pathologies and Neurodegenerative Disease

Abhimanyu S Ahuja,1,* Alfredo A Paredes III,2,* Mallory LS Eisel,3,* Cole Miller,4 Nina Truong,3 Julie Falardeau1 1Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, Portland, OR, USA; 2Charles E. Schmidt College of Medicine, Florida Atlantic University, Boca Raton, FL, USA; 3College of Medicine, Florida State University, Tallahassee, FL, USA; 4Leonard M. Miller School of Medicine, University of Miami, Miami, FL, USA*These authors contributed equally to this workCorrespondence: Abhimanyu S Ahuja, Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, 515 SW Campus Drive, Portland, OR, 97239, USA, Email ahujaa@ohsu.edu Julie Falardeau, Department of Ophthalmology, Casey Eye Institute, Oregon Health and Science University, 515 SW Campus Drive, Portland, OR, 97239, USA, Email falardea@ohsu.eduAbstract: Artificial intelligence (AI) is rapidly reshaping neuro-ophthalmic care by extracting clinically significant information from imaging, biomarkers, and patient-level clinical data. We review recent advances across neurodegenerative disease detection using retinal biomarkers, automated recognition of optic disc swelling and its mimics, glaucoma screening and quantification, and classification of hereditary optic neuropathies. Using fundus photography and optical coherence tomography (OCT), contemporary machine learning (ML) systems, including deep learning as well as other supervised learning models, report strong discrimination for papilledema versus pseudopapilledema, non-arteritic anterior ischemic optic neuropathy (NAION) against similar presenting entities, and glaucomatous damage including indirect estimation of retinal nerve fiber layer (RNFL) thickness. Early work also suggests that retinal features can aid detection of mild cognitive impairment (MCI) and major neurocognitive disease. However, despite promising results, most studies remain retrospective and single-center, while focusing on imaging-only, limiting generalizability and clinical interpretability. Therefore a variety of challenges related to dataset heterogeneity, overfitting, limited external validation, and the gap between high diagnostic accuracy and practical clinical utility remain unresolved. Future prospective, multicenter evaluations focusing on integrating multimodal clinical data through explainable AI systems are necessary to improve diagnostic consistency, shorten time to care, and expand access for underserved populations.Keywords: artificial intelligence, neuro-ophthalmology, deep learning, machine learning, support vector machine, extreme learning machine