AUTHOR=Ricciardi Antonio , Grussu Francesco , Kanber Baris , Prados Ferran , Yiannakas Marios C. , Solanky Bhavana S. , Riemer Frank , Golay Xavier , Brownlee Wallace , Ciccarelli Olga , Alexander Daniel C. , Gandini Wheeler-Kingshott Claudia A. M. 

TITLE=Patterns of inflammation, microstructural alterations, and sodium accumulation define multiple sclerosis subtypes after 15 years from onset

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 17 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2023.1060511

DOI=10.3389/fninf.2023.1060511

ISSN=1662-5196

ABSTRACT=Conventional MRI is routinely used for the characterisation of pathological changes in multiple sclerosis (MS), but due to its lack of specificity is unable to provide accurate prognoses, explain disease heterogeneity and reconcile the gap between observed clinical symptoms and radiological evidence. Quantitative MRI provides measures of physiological abnormalities, otherwise invisible to conventional MRI, that correlate with MS severity. Analysing quantitative MRI measures through machine learning techniques has been shown to improve the understanding of the underlying disease by better delineating its alteration patterns.
In this retrospective study, a cohort of healthy controls (HC) and MS patients with different subtypes, followed up 15 years from clinically isolated syndrome (CIS), was analysed to produce a multi-modal set of quantitative MRI features encompassing relaxometry, microstructure, sodium ion concentration and tissue volumetry. Random forest classifiers were used to train a model able to discriminate between HC, CIS, relapsing remitting (RR) and secondary progressive (SP) MS patients based on these features and, for each classification task, to identify the relative contribution of each MRI-derived tissue property to the classification task itself.
Average classification accuracy scores of 99% and 95% were obtained when discriminating HC and CIS versus SP, respectively; 82% and 83% for HC and CIS versus RR; 76% for RR versus SP, and 79% for HC versus CIS. Different patterns of alterations were observed for each classification task, offering key insights in the understanding of MS phenotypes pathophysiology: atrophy and relaxometry emerged particularly in the classification of HC and CIS versus MS, relaxometry within lesions in RR versus SP, sodium ion concentration in HC versus CIS, and microstructural alterations were involved across all tasks.