Combined structural and functional patterns discriminating upper limb motor disability in multiple sclerosis using multivariate approaches
A structural or functional pattern of neuroplasticity that could systematically discriminate between people with impaired and preserved motor performance could help us to understand the brain networks contributing to preservation or compensation of behavior in multiple sclerosis (MS). This study aimed to (1) investigate whether a machine learning-based technique could accurately classify MS participants into groups defined by upper extremity function (i.e. motor function preserved (MP) vs. motor function impaired (MI)) based on their regional grey matter measures (GMM, cortical thickness and deep grey matter volume) and inter-regional functional connection (FC), (2) investigate which features (GMM, FC, or GMM + FC) could classify groups more accurately, and (3) identify the multivariate patterns of GMM and FCs that are most discriminative between MP and MI participants, and between each of these groups and the healthy controls (HCs). With 26 MP, 25 MI, and 21 HCs (age and sex matched) underwent T1-weighted and resting-state functional MRI at 3 T, we applied support vector machine (SVM) based classification to learn discriminant functions indicating regions in which GMM or between which FCs were most discriminative between groups. This study demonstrates that there exist structural and FC patterns sufficient for correct classification of upper limb motor ability of people with MS. The classifier with GMM + FC features yielded the highest accuracy of 85.61 % (p < 0.001) to distinguish between the MS groups using leave-one-out cross-validation. It suggests that a machine-learning approach combining structural and functional features is useful for identifying the specific neural substrates that are necessary and sufficient to preserve motor function among people with MS.
KeywordsCortical thickness Deep grey matter volume Functional connectivity Motor disability Multiple sclerosis Multivariate analysis Support vector machine
We thank Dr. Douglas Arnold, Dr. David Araujo, Serge Gallant, Dr. Elena Lebedeva, Afiqua Yusef, Ben Whatley, Rebecca Sussex, Haz-Edine Assemlal, Dr. Kunio Nakamura and Stanley Hum for their contributions to data collection and processing.
Compliance with ethical standards
This study was funded by the Canadian Institutes of Health Research (grant number: MOP119428), and by the Research Institute of the McGill University Health Centre.
Conflict of interest
Author Jidan Zhong, Author David Qixiang Chen, Author Julia C. Nantes, Author Scott A. Holmes, Author Mojgan Hodaie and Author Lisa Koski declare no conflicts of interest.
This study was approved by the Research Ethics Board of the Montreal Neurological Institute and Hospital. All procedures performed in this study involving human participants were in accordance with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- Audoin, B., Ibarrola, D., Malikova, I., Soulier, E., Confort-Gouny, S., Duong, M. V. A., et al. (2007). Onset and underpinnings of white matter atrophy at the very early stage of multiple sclerosis–a two-year longitudinal MRI/MRSI study of corpus callosum. Multiple Sclerosis (Houndmills, Basingstoke, England), 13(1), 41–51.CrossRefGoogle Scholar
- Basile, B., Castelli, M., Monteleone, F., Nocentini, U., Caltagirone, C., Centonze, D., et al. (2013). Functional connectivity changes within specific networks parallel the clinical evolution of multiple sclerosis. Multiple Sclerosis (Houndmills, Basingstoke, England), 20(8), 1050–1057.CrossRefGoogle Scholar
- Brodersen, K. H., Ong, C. S., Stephan, K. E., & Buhmann, J. M. (2010). The balanced accuracy and its posterior distribution. In Proceedings of the 2010 20th International Conference on Pattern Recognition (ICPR ‘10), 3121-3124. Washington, DC: IEEE Computer Society, doi: 10.1109/ICPR.2010.764
- Calabrese, M., Rinaldi, F., Grossi, P., Mattisi, I., Bernardi, V., Favaretto, A., et al. (2010). Basal ganglia and frontal/parietal cortical atrophy is associated with fatigue in relapsing-remitting multiple sclerosis. Multiple Sclerosis (Houndmills, Basingstoke, England), 16(10), 1220–1228.CrossRefGoogle Scholar
- Chang, Y.-W., & Lin, C.-J. (2008). Feature ranking using linear svm. Journal of Machine Learning Research: Workshop and Conference Proceedings, 3, 53–64.Google Scholar
- Filippi, M., Rovaris, M., Inglese, M., Barkhof, F., De Stefano, N., Smith, S., et al. (2004). Interferon beta-1a for brain tissue loss in patients at presentation with syndromes suggestive of multiple sclerosis: a randomised, double-blind, placebo-controlled trial. The Lancet, 364(9444), 1489–1496.CrossRefGoogle Scholar
- Filippi, M., Valsasina, P., Vacchi, L., Leavitt, V., Comi, G., Falini, A., & Rocca, M. (2015). Consistent decreased functional connectivity among the main cortical and subcortical functional networks in MS: relationship with disability and cognitive impairment. Neurology, 84(14), Supplement P6.133.Google Scholar
- Fix, J. D. (2008). Basal Ganglia and the Striatal Motor System. Neuroanatomy (Board Review Series) (4th ed.), Baltimore: Wulters Kluwer & Lippincott Wiliams & Wilkins, 274–281.Google Scholar
- Francis, S. J. (2004). Automatic lesion identification in MRI of multiple sclerosis patients. Montreal: McGill University.Google Scholar
- Honey, C. J., Sporns, O., Cammoun, L., Gigandet, X., Thiran, J. P., Meuli, R., & Hagmann, P. (2009). Predicting human resting-state functional connectivity from structural connectivity. Proceedings of the National Academy of Sciences of the United States of America, 106(6), 2035–2040.CrossRefPubMedPubMedCentralGoogle Scholar
- Johnson, D. E. (1998). Applied multivariate methods for data analysts. Pacific Grove: Duxbury Press.Google Scholar
- Kalkers, N. F., Polman, C. H., & Uitdehaag, B. M. J. (2001). Measuring clinical disability: the MS functional composite. Int. MSJ, 8(3), 79–87.Google Scholar
- Mahmoudi, A., Takerkart, S., Regragui, F., Boussaoud, D., & Brovelli, A. (2012). Multivoxel pattern analysis for fMRI data: A review. Computational and Mathematical Methods in Medicine, 2012, Article ID 961257.Google Scholar
- Makris N, Kennedy DN, Meyer J, Worth A, Caviness VS, Jr., Seidman L, Goldstein J, Goodman J, Hoge E, Macpherson C, Tourville J, Klaveness S, Hodge SM, Melrose R, Rauch S, Kim H, Harris G, Boehland A, Glode B, Koch J, Segal E, Sonricker A, Dieterich M, Papadimitriou G, Normandin JJ, Cullen N, Boriel D, Sanders H (2004). Segmentation manual. Center for Morphometric Analysis (CMA), Massachusetts General Hospital (MGH), http://www.cma.mgh.harvard.edu/manuals/segmentation/.Google Scholar
- Nantes, J. C., Zhong, J., Holmes, S. A., Whatley, B., Narayanan, S., Lapierre, Y., & Koski, L. M. (2015). Intracortical inhibition abnormality during the remission phase of multiple sclerosis is related to upper limb dexterity and lesions. Clinical Neurophysiology. doi: 10.1016/j.clinph.2015.08.011.PubMedGoogle Scholar
- Pagani, E., Rocca, M. A., Gallo, A., Rovaris, M., Martinelli, V., Comi, G., & Filippi, M. (2005). Regional brain atrophy evolves differently in patients with multiple sclerosis according to clinical phenotype. American Journal of Neuroradiology, 26(2), 341–346.Google Scholar
- Sripada, R. K., King, A. P., Garfinkel, S. N., Wang, X., Sripada, C. S., Welsh, R. C., & Liberzon, I. (2012). Altered resting-state amygdala functional connectivity in men with posttraumatic stress disorder. Journal of Psychiatry and Neuroscience, 37(4), 241–249.CrossRefPubMedPubMedCentralGoogle Scholar
- Stevens, J. S., Jovanovic, T., Fani, N., Ely, T. D., Glover, E. M., Bradley, B., & Ressler, K. J. (2013). Disrupted amygdala-prefrontal functional connectivity in civilian women with posttraumatic stress disorder. Journal of Psychiatric Research, 47(10), 1469–1478.CrossRefPubMedPubMedCentralGoogle Scholar
- Yozbatiran, N., Baskurt, F., Baskurt, Z., Ozakbas, S., & Idiman, E. (2006). Motor assessment of upper extremity function and its relation with fatigue, cognitive function and quality of life in multiple sclerosis patients. Journal of the Neurological Sciences, 246(1–2), 117–122.CrossRefPubMedGoogle Scholar
- Zar, J. H. (2010). Biostatistical analysis. New Jersey USA: Prentice Hall.Google Scholar