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

Alberto Montolío; Alejandro Martín-Gallego; José Cegoñino; Elvira Orduna; Elisa Vilades; Elena Garcia-Martin; Amaya Pérez Del Palomar

doi:10.1016/j.compbiomed.2021.104416

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

Comput Biol Med. 2021 Jun:133:104416. doi: 10.1016/j.compbiomed.2021.104416. Epub 2021 Apr 26.

Authors

Alberto Montolío¹, Alejandro Martín-Gallego¹, José Cegoñino¹, Elvira Orduna², Elisa Vilades², Elena Garcia-Martin², Amaya Pérez Del Palomar³

Affiliations

¹ Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain.
² Ophthalmology Department, Miguel Servet University Hospital, Zaragoza, Spain; GIMSO Research and Innovative Group, Aragon Institute for Health Research (IIS Aragon), Zaragoza, Spain.
³ Group of Biomaterials, Aragon Institute of Engineering Research (I3A), University of Zaragoza, Zaragoza, Spain; Department of Mechanical Engineering, University of Zaragoza, Zaragoza, Spain. Electronic address: amaya@unizar.es.

PMID: 33946022
DOI: 10.1016/j.compbiomed.2021.104416

Abstract

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.

Keywords: Expanded disability status scale; Machine learning; Multiple sclerosis; Optical coherence tomography; Retinal nerve fiber layer.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Bayes Theorem
Humans
Machine Learning
Multiple Sclerosis* / diagnostic imaging
Nerve Fibers
Neurodegenerative Diseases*
Tomography, Optical Coherence