Swept source optical coherence tomography to early detect multiple sclerosis disease. The use of machine learning techniques

Objective To compare axonal loss in ganglion cells detected with swept-source optical coherence tomography (SS-OCT) in eyes of patients with multiple sclerosis (MS) versus healthy controls using different machine learning techniques. To analyze the capability of machine learning techniques to improve the detection of retinal nerve fiber layer (RNFL) and the complex Ganglion Cell Layer–Inner plexiform layer (GCL+) damage in patients with multiple sclerosis and to use the SS-OCT as a biomarker to early predict this disease. Methods Patients with relapsing-remitting MS (n = 80) and age-matched healthy controls (n = 180) were enrolled. Different protocols from the DRI SS-OCT Triton system were used to obtain the RNFL and GCL+ thicknesses in both eyes. Macular and peripapilar areas were analyzed to detect the zones with higher thickness decrease. The performance of different machine learning techniques (decision trees, multilayer perceptron and support vector machine) for identifying RNFL and GCL+ thickness loss in patients with MS were evaluated. Receiver-operating characteristic (ROC) curves were used to display the ability of the different tests to discriminate between MS and healthy eyes in our population. Results Machine learning techniques provided an excellent tool to predict MS disease using SS-OCT data. In particular, the decision trees obtained the best prediction (97.24%) using RNFL data in macular area and the area under the ROC curve was 0.995, while the wide protocol which covers an extended area between macula and papilla gave an accuracy of 95.3% with a ROC of 0.998. Moreover, it was obtained that the most significant area of the RNFL to predict MS is the macula just surrounding the fovea. On the other hand, in our study, GCL+ did not contribute to predict MS and the different machine learning techniques performed worse in this layer than in RNFL. Conclusions Measurements of RNFL thickness obtained with SS-OCT have an excellent ability to differentiate between healthy controls and patients with MS. Thus, the use of machine learning techniques based on these measures can be a reliable tool to help in MS diagnosis.

[1]  Alexander Klistorner,et al.  Retinal thickness measured with optical coherence tomography and risk of disability worsening in multiple sclerosis: a cohort study , 2016, The Lancet Neurology.

[2]  O. Garcea,et al.  Optical coherence tomography as a biomarker of neurodegeneration in multiple sclerosis: A review. , 2018, Multiple sclerosis and related disorders.

[3]  Fiona Costello,et al.  Retinal imaging with optical coherence tomography: a biomarker in multiple sclerosis? , 2018, Eye and brain.

[4]  M. Racke,et al.  Multiple Sclerosis: Current Status and Strategies for the Future , 2003 .

[5]  Richard A Armstrong,et al.  Statistical guidelines for the analysis of data obtained from one or both eyes , 2013, Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians.

[6]  M. C. Leske,et al.  The Lens Opacities Classification System III , 1993 .

[7]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[8]  Vicente Polo,et al.  Neural networks to identify multiple sclerosis with optical coherence tomography , 2013, Acta ophthalmologica.

[9]  Andreas Ziegler,et al.  Risk estimation and risk prediction using machine-learning methods , 2012, Human Genetics.

[10]  Board on Neuroscience.  Multiple Sclerosis:: Current Status and Strategies for the Future , 2001 .

[11]  Ming Yang,et al.  Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection: decision tree, k-nearest neighbors, and support vector machine , 2016, Simul..

[12]  S. A. Meyer,et al.  Visual dysfunction in multiple sclerosis correlates better with optical coherence tomography derived estimates of macular ganglion cell layer thickness than peripapillary retinal nerve fiber layer thickness , 2011, Multiple sclerosis.

[13]  Eric B. Baum,et al.  On the capabilities of multilayer perceptrons , 1988, J. Complex..

[14]  C. Brodley,et al.  Exploration of machine learning techniques in predicting multiple sclerosis disease course , 2017, PloS one.

[15]  B. Uitdehaag,et al.  Timing of retinal neuronal and axonal loss in MS: a longitudinal OCT study , 2016, Journal of Neurology.

[16]  L. Pablo,et al.  Artificial Neural Network Techniques to Improve the Ability of Optical Coherence Tomography to Detect Optic Neuritis , 2015, Seminars in ophthalmology.

[17]  Elena Garcia-Martin,et al.  Retinal layer segmentation in patients with multiple sclerosis using spectral domain optical coherence tomography. , 2014, Ophthalmology.

[18]  Jean-Philippe Vergne,et al.  Buzz Factor or Innovation Potential: What Explains Cryptocurrencies’ Returns? , 2017, PloS one.

[19]  U. Schmidt-Erfurth,et al.  High Resolution Spectral Domain Optical Coherence Tomography (SD-OCT) in Multiple Sclerosis: The First Follow Up Study over Two Years , 2011, PloS one.

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[21]  Gabriel Pardo,et al.  Reduced retinal nerve fiber layer and macular thickness in patients with multiple sclerosis with no history of optic neuritis identified by the use of spectral domain high-definition optical coherence tomography , 2011, Journal of Clinical Neuroscience.

[22]  Marco Rovaris,et al.  A single, early magnetic resonance imaging study in the diagnosis of multiple sclerosis. , 2009, Archives of neurology.

[23]  J. Frederiksen,et al.  Retinal ganglion cell analysis in multiple sclerosis and optic neuritis: a systematic review and meta-analysis , 2017, Journal of Neurology.

[24]  I. Grabska-Liberek,et al.  Peripapillary retinal nerve fiber layer thickness measured by optical coherence tomography in different clinical subtypes of multiple sclerosis. , 2019, Multiple sclerosis and related disorders.

[25]  S. Saidha,et al.  Can Optical Coherence Tomography Be Used to Guide Treatment Decisions in Adult or Pediatric Multiple Sclerosis? , 2018, Current Treatment Options in Neurology.

[26]  David S. Wishart,et al.  Applications of Machine Learning in Cancer Prediction and Prognosis , 2006, Cancer informatics.

[27]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[28]  F Pierelli,et al.  Correlation between morphological and functional retinal impairment in multiple sclerosis patients. , 1999, Investigative ophthalmology & visual science.

[29]  T. Olsson,et al.  The Temporal Retinal Nerve Fiber Layer Thickness Is the Most Important Optical Coherence Tomography Estimate in Multiple Sclerosis , 2017, Front. Neurol..

[30]  M. Schwartz,et al.  The retina as a window to the brain—from eye research to CNS disorders , 2013, Nature Reviews Neurology.

[31]  Ian H. Witten,et al.  Data Mining, Fourth Edition: Practical Machine Learning Tools and Techniques , 2016 .

[32]  Dimitrios I. Fotiadis,et al.  Machine learning applications in cancer prognosis and prediction , 2014, Computational and structural biotechnology journal.

[33]  David H. Miller,et al.  Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria , 2017, The Lancet Neurology.

[34]  I. Zubizarreta,et al.  The multiple sclerosis visual pathway cohort: understanding neurodegeneration in MS , 2014, BMC Research Notes.

[35]  Elena Garcia-Martin,et al.  Optical Coherence Tomography as a Biomarker for Diagnosis, Progression, and Prognosis of Neurodegenerative Diseases , 2016, Journal of ophthalmology.

[36]  Alexander Klistorner,et al.  Retinal layer segmentation in multiple sclerosis: a systematic review and meta-analysis , 2017, The Lancet Neurology.

[37]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[38]  J. Kai,et al.  Can machine-learning improve cardiovascular risk prediction using routine clinical data? , 2017, PloS one.

[39]  J Martin,et al.  Effect of optic neuritis on progressive axonal damage in multiple sclerosis patients , 2011, Multiple sclerosis.

[40]  P M Matthews,et al.  Size-selective neuronal changes in the anterior optic pathways suggest a differential susceptibility to injury in multiple sclerosis. , 2001, Brain : a journal of neurology.