AI-Based Classification of Multiple Sclerosis Using OCT Retinal Layer Thickness Across Two Centers

Background: The latest revision of the McDonald criteria for diagnosis of multiple sclerosis (MS) establishes that the optic nerve can serve as a fifth anatomical location within the central nervous system for diagnosis. Optical coherence tomography (OCT) images can serve as evidence for this purpose. Objective: To assess the accuracy of automated artificial-intelligence-based classification of MS patients using OCT data obtained from two different centers. Methods: OCT data were collected from two centers using standardized APOSTEL-based protocols and similar equipment. Retinal layer thicknesses-mean and standard deviation (STD) values-were analyzed in four layers and in six regions per layer per eye. A support vector machine classifier with recursive feature elimination and Shapley additive explanations value analysis was applied to identify the most relevant features and maximize classification accuracy between control subject and MS patient eyes. Results: The database drawn from two hospitals comprised 112 eyes with MS without prior history of optic neuritis and 193 eyes of control subjects. The classifier achieved maximum accuracy (0.8459) using 20 input features. The mean and STD metrics had similar importance, with the most influential layers being the ganglion cell layer, inner plexiform layer, and the inner retinal layer complex. Key regions included the papillomacular bundle and the superior temporal perimacular area. Conclusions: OCT data facilitates highly accurate MS diagnosis across different centers. Artificial intelligence assessment could facilitate automated classification. These findings provide evidence of the important role of the optic nerve in MS diagnosis.