Related Experiment Video
Updated: Jun 15, 2026
Dynamic Visual Tests to Identify and Quantify Visual Damage and Repair Following Demyelination in Optic Neuritis Patients
Published on: April 14, 2014
The Role of Optical Coherence Tomography Criteria and Machine Learning in Multiple Sclerosis and Optic Neuritis
Rachel C Kenney1, Mengling Liu1, Lisena Hasanaj1
1From the Departments of Neurology (R.C.K., L.H., B.J., S.G., L.J. Balcer) and Population Health (R.C.K., M.L., L.E.T., Y.C., L.J. Balcer), New York University Grossman School of Medicine; Al-Bahar Ophthalmology Center (A.A.A.-H., R.B.), Ibn Sina Hospital, Kuwait City, Kuwait; Mulier Institute (L.J. Balk), Centre for Research on Sports in Society, Utrecht, the Netherlands; Experimental and Clinical Research Center (A.B., A. Papadopoulou, F.P., H.Z.), Max Delbrueck Center for Molecular Medicine and Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin; Department of Neurology (A.B.), University of California, Irvine; Department of Neurology (P.A.C., S.S.), Johns Hopkins University, Baltimore, MD; Laboratory of Neuroimmunology (E.F., T.C.F.), of Professor Lawrence Steinman, Stanford University School of Medicine, Palo Alto, CA; Institute of Clinical Neuroimmunology (J.H.), LMU Hospital, Ludwig Maximilians Universität München; Data Integration for Future Medicine Consortium (DIFUTURE) (J.H.), Ludwig-Maximilians University, Munich; Department of Neurology (B.H., B.K., T.K.), Klinikum rechts der Isar, School of Medicine, Technical University of Munich; Munich Cluster for Systems Neurology (SyNergy) (B.H., T.K.), Germany; Bascom Palmer Eye Institute (H.J.), Department of Neurology, University of Miami Miller School of Medicine, FL; Vita-Salute University & Hospital San Raffaele (L.L., M.P.), Milano, Italy; Center of Neuroimmunology and Department of Neurology (E.H.M.-L., P.V.), Hospital Clinic of Barcelona, Institut d'Investigacions Biomèdiques August Pi Sunyer (IDIBAPS), University of Barcelona, Spain; Neurologic Clinic and Policlinic (A. Papadopoulou), MS Center and Research Center for Clinical Neuroimmunology and Neuroscience (RCN2NB) Basel, University Hospital Basel and University of Basel, Switzerland; NeuroCure Clinical Research Center (F.P., H.Z.), Charité-Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Germany; Moorfields Eye Hospital (Axel Petzold), London; The National Hospital for Neurology and Neurosurgery (A. Petzold), Queen Square, UCL Institute of Neurology, United Kingdom; Dutch Neuro-ophthalmology Expertise Centre, Amsterdam UMC, the Netherlands; Oregon Health and Science University (H.I.), Portland; Department of Ophthalmology (J.S.S., G.W., S.G., Laura J. Balcer), New York University Grossman School of Medicine; Departments of Biomedical Engineering and Electrical and Computer Engineering (J.S.S.), New York University Tandon School of Engineering, Brooklyn; Center for Neural Science (J.S.S.), New York University; and Neuroscience Institute (J.S.S.), NYU Langone Health. Dr. Kenney is currently at the Department of Radiology and Radiological Sciences, Vanderbilt University Medical Center, Nashville, TN.
Background And Objectives:
Recent studies have suggested that intereye differences (IEDs) in peripapillary retinal nerve fiber layer (pRNFL) or ganglion cell + inner plexiform (GCIPL) thickness by spectral domain optical coherence tomography (SD-OCT) may identify people with a history of unilateral optic neuritis (ON). However, this requires further validation. Machine learning classification may be useful for validating thresholds for OCT IEDs and for examining added utility for visual function tests, such as low-contrast letter acuity (LCLA), in the diagnosis of people with multiple sclerosis (PwMS) and for unilateral ON history.
Methods:
Participants were from 11 sites within the International Multiple Sclerosis Visual System consortium. pRNFL and GCIPL thicknesses were measured using SD-OCT. A composite score combining OCT and visual measures was compared individual measurements to determine the best model to distinguish PwMS from controls. These methods were also used to distinguish those with a history of ON among PwMS. Receiver operating characteristic (ROC) curve analysis was performed on a training data set (2/3 of cohort) and then applied to a testing data set (1/3 of cohort). Support vector machine (SVM) analysis was used to assess whether machine learning models improved diagnostic capability of OCT.
Results:
Among 1,568 PwMS and 552 controls, variable selection models identified GCIPL IED, average GCIPL thickness (both eyes), and binocular 2.5% LCLA as most important for classifying PwMS vs controls. This composite score performed best, with area under the curve (AUC) = 0.89 (95% CI 0.85-0.93), sensitivity = 81%, and specificity = 80%. The composite score ROC curve performed better than any of the individual measures from the model (p < 0.0001). GCIPL IED remained the best single discriminator of unilateral ON history among PwMS (AUC = 0.77, 95% CI 0.71-0.83, sensitivity = 68%, specificity = 77%). SVM analysis performed comparably with standard logistic regression models.
Discussion:
A composite score combining visual structure and function improved the capacity of SD-OCT to distinguish PwMS from controls. GCIPL IED best distinguished those with a history of unilateral ON. SVM performed as well as standard statistical models for these classifications.
Classification Of Evidence:
This study provides Class III evidence that SD-OCT accurately distinguishes multiple sclerosis from normal controls as compared with clinical criteria.
