Machine learning in diagnosis and disability prediction of multiple sclerosis using optical coherence tomography

Montolío A. (Universidad de Zaragoza) ; Martín-Gallego A. ; Cegoñino J. (Universidad de Zaragoza) ; Orduna E. (Universidad de Zaragoza) ; Vilades E. (Universidad de Zaragoza) ; Garcia-Martin E. (Universidad de Zaragoza) ; Pérez del Palomar A. (Universidad de Zaragoza)

Resumen: 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)

Idioma: Inglés

DOI: 10.1016/j.compbiomed.2021.104416

Año: 2021

Publicado en: Computers in biology and medicine 133 (2021), 104416 [13 pp]
ISSN: 0010-4825

Factor impacto JCR: 6.698 (2021)

Categ. JCR: BIOLOGY rank: 13 / 94 = 0.138 (2021) - Q1 - T1
Categ. JCR: MATHEMATICAL & COMPUTATIONAL BIOLOGY rank: 6 / 57 = 0.105 (2021) - Q1 - T1
Categ. JCR: ENGINEERING, BIOMEDICAL rank: 22 / 98 = 0.224 (2021) - Q1 - T1
Categ. JCR: COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS rank: 24 / 112 = 0.214 (2021) - Q1 - T1

Factor impacto CITESCORE: 8.2 - Medicine (Q1) - Computer Science (Q1)

Factor impacto SCIMAGO: 1.309 - Health Informatics (Q1) - Computer Science Applications (Q1)

Financiación: info:eu-repo/grantAgreement/ES/ISCIII/PI17-01726
Financiación: info:eu-repo/grantAgreement/ES/MICIU/BES-2017-080384
Financiación: info:eu-repo/grantAgreement/ES/MINECO/DPI2016-79302-R

Tipo y forma: Artículo (Versión definitiva)

Área (Departamento): Área Oftalmología (Dpto. Cirugía)
Área (Departamento): Área Óptica (Dpto. Física Aplicada)
Área (Departamento): Área Mec.Med.Cont. y Teor.Est. (Dpto. Ingeniería Mecánica)