000152982 001__ 152982
000152982 005__ 20251017144551.0
000152982 0247_ $$2doi$$a10.1167/tvst.14.2.14
000152982 0248_ $$2sideral$$a143473
000152982 037__ $$aART-2025-143473
000152982 041__ $$aeng
000152982 100__ $$aOrtiz, Miguel
000152982 245__ $$aNew Method of Early RRMS Diagnosis Using OCT-Assessed Structural Retinal Data and Explainable Artificial Intelligence
000152982 260__ $$c2025
000152982 5060_ $$aAccess copy available to the general public$$fUnrestricted
000152982 5203_ $$aPurpose: The purpose of this study was to provide the development of a method to classify optical coherence tomography (OCT)-assessed retinal data in the context of automatic diagnosis of early-stage multiple sclerosis (MS) with decision explanation.
Methods: The database used contains recordings from 79 patients with recently diagnosed relapsing-remitting multiple sclerosis (RRMS) and no history of optic neuritis and from 69 age-matched healthy control subjects. Analysis was performed on the thicknesses (average right and left eye value and inter-eye difference) of the macular retinal nerve fiber layer (mRNFL), macular ganglion cell layer (mGCL), macular inner plexiform layer (mIPL), and macular inner retinal complex layer (mIRL), dividing the macular area into six analysis zones. Recursive feature extraction (RFE) and Shapley additive explanations (SHAP) are combined to rank relevant features and select the subset that maximizes classifier (support vector machine [SVM]) performance.
Results: Of the initial 48 features, 20 were identified as maximizing classifier accuracy (n = 0.9257). The SHAP values indicate that average thickness has greater relevance than inter-eye difference, that the mGCL and mRNFL are the most influential structures, and that the peripheral papillomacular bundle and the supero-temporal quadrant are the zones most affected.
Conclusions: This approach improves the success rate of automatic diagnosis of early-stage RRMS and enhances clinical decision making transparency.
000152982 536__ $$9info:eu-repo/grantAgreement/ES/DGA/B23-23R$$9info:eu-repo/grantAgreement/ES/DGA/B50-24$$9info:eu-repo/grantAgreement/ES/ISCIII/PI23-00935$$9info:eu-repo/grantAgreement/ES/ISCIII/RD24-0007-0022$$9info:eu-repo/grantAgreement/ES/ISCIII-RICORDS/RD21-0002-0050
000152982 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es
000152982 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion
000152982 700__ $$aPueyo, Ana
000152982 700__ $$aDongil, Francisco J.
000152982 700__ $$aBoquete, Luciano
000152982 700__ $$aSánchez-Morla, Eva M.
000152982 700__ $$aBarea, Rafael
000152982 700__ $$aMiguel-Jimenez, Juan M.
000152982 700__ $$aLópez-Dorado, Almudena
000152982 700__ $$0(orcid)0000-0001-9411-5834$$aVilades, Elisa$$uUniversidad de Zaragoza
000152982 700__ $$aRodrigo, María J.$$uUniversidad de Zaragoza
000152982 700__ $$aCordon, Beatriz$$uUniversidad de Zaragoza
000152982 700__ $$0(orcid)0000-0001-6258-2489$$aGarcia-Martin, Elena$$uUniversidad de Zaragoza
000152982 7102_ $$11013$$2646$$aUniversidad de Zaragoza$$bDpto. Cirugía$$cÁrea Oftalmología
000152982 773__ $$g14, 2 (2025), 14 [9 pp.]$$pTransl. vis. sci. technol.$$tTranslational Vision Science and Technology$$x2164-2591
000152982 8564_ $$s3695656$$uhttps://zaguan.unizar.es/record/152982/files/texto_completo.pdf$$yVersión publicada
000152982 8564_ $$s2559759$$uhttps://zaguan.unizar.es/record/152982/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada
000152982 909CO $$ooai:zaguan.unizar.es:152982$$particulos$$pdriver
000152982 951__ $$a2025-10-17-14:11:47
000152982 980__ $$aARTICLE