147631 20241220131256.0 doi 10.1016/j.compbiomed.2021.104416 sideral 126259 ART-2021-126259 eng Montolío A. Universidad de Zaragoza (orcid)0000-0001-7248-4399 Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography 2021 Background: Multiple sclerosis (MS) is a neurodegenerative disease that affects the central nervous system, especially the brain, spinal cord, and optic nerve. Diagnosis of this disease is a very complex process and generally requires a lot of time. In addition, treatments are applied without any information on the disability course in each MS patient. For these two reasons, the objective of this study was to improve the MS diagnosis and predict the long-term course of disability in MS patients based on clinical data and retinal nerve fiber layer (RNFL) thickness, measured by optical coherence tomography (OCT). Material and methods: A total of 104 healthy controls and 108 MS patients, 82 of whom had a 10-year follow-up, were enrolled. Classification algorithms such as multiple linear regression (MLR), support vector machines (SVM), decision tree (DT), k-nearest neighbours (k-NN), Naïve Bayes (NB), ensemble classifier (EC) and long short-term memory (LSTM) recurrent neural network were tested to develop two predictive models: MS diagnosis model and MS disability course prediction model. Results: For MS diagnosis, the best result was obtained using EC (accuracy: 87.7%; sensitivity: 87.0%; specificity: 88.5%; precision: 88.7%; AUC: 0.8775). In line with this good performance, the accuracy was 85.4% using k-NN and 84.4% using SVM. And, for long-term prediction of MS disability course, LSTM recurrent neural network was the most appropriate classifier (accuracy: 81.7%; sensitivity: 81.1%; specificity: 82.2%; precision: 78.9%; AUC: 0.8165). The use of MLR, SVM and k-NN also showed a good performance (AUC = 0.8). Conclusions: This study demonstrated that machine learning techniques, using clinical and OCT data, can help establish an early diagnosis and predict the course of MS. This advance could help clinicians select more specific treatments for each MS patient. Therefore, our findings underscore the potential of RNFL thickness as a reliable MS biomarker. © 2021 The Author(s) Access copy available to the general public Unrestricted info:eu-repo/grantAgreement/ES/ISCIII/PI17-01726 info:eu-repo/grantAgreement/ES/MICIU/BES-2017-080384 info:eu-repo/grantAgreement/ES/MINECO/DPI2016-79302-R info:eu-repo/semantics/openAccess by-nc-nd http://creativecommons.org/licenses/by-nc-nd/3.0/es/ 6.698 2021 BIOLOGY 13 / 94 = 0.138 2021 Q1 T1 MATHEMATICAL & COMPUTATIONAL BIOLOGY 6 / 57 = 0.105 2021 Q1 T1 ENGINEERING, BIOMEDICAL 22 / 98 = 0.224 2021 Q1 T1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS 24 / 112 = 0.214 2021 Q1 T1 1.309 2021 Health Informatics 2021 Q1 Computer Science Applications 2021 Q1 8.2 2021 info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion Martín-Gallego A. Cegoñino J. Universidad de Zaragoza (orcid)0000-0002-2967-6747 Orduna E. Universidad de Zaragoza (orcid)0000-0003-2710-1875 Vilades E. Universidad de Zaragoza (orcid)0000-0001-9411-5834 Garcia-Martin E. Universidad de Zaragoza (orcid)0000-0001-6258-2489 Pérez del Palomar A. Universidad de Zaragoza (orcid)0000-0003-0669-777X 1013 646 Universidad de Zaragoza Dpto. Cirugía Área Oftalmología 2002 647 Universidad de Zaragoza Dpto. Física Aplicada Área Óptica 5004 605 Universidad de Zaragoza Dpto. Ingeniería Mecánica Área Mec.Med.Cont. y Teor.Est. 133 (2021), 104416 [13 pp] Comput. biol. med. Computers in biology and medicine 0010-4825 6712339 http://zaguan.unizar.es/record/147631/files/texto_completo.pdf Versión publicada 2422273 http://zaguan.unizar.es/record/147631/files/texto_completo.jpg?subformat=icon icon Versión publicada oai:zaguan.unizar.es:147631 articulos driver 2024-12-20-12:00:51 ARTICLE