Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2021 Apr 6;12(1):2078.
doi: 10.1038/s41467-021-22265-2.

Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data

Arman Eshaghi  1   2 , Alexandra L Young  3   4 , Peter A Wijeratne  3 , Ferran Prados  5   3   6 , Douglas L Arnold  7 , Sridar Narayanan  7 , Charles R G Guttmann  8 , Frederik Barkhof  5   3   9   10 , Daniel C Alexander  3 , Alan J Thompson  5 , Declan Chard #  5   11 , Olga Ciccarelli #  5   11
Affiliations

Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data

Arman Eshaghi et al. Nat Commun. .

Erratum in

Abstract

Multiple sclerosis (MS) can be divided into four phenotypes based on clinical evolution. The pathophysiological boundaries of these phenotypes are unclear, limiting treatment stratification. Machine learning can identify groups with similar features using multidimensional data. Here, to classify MS subtypes based on pathological features, we apply unsupervised machine learning to brain MRI scans acquired in previously published studies. We use a training dataset from 6322 MS patients to define MRI-based subtypes and an independent cohort of 3068 patients for validation. Based on the earliest abnormalities, we define MS subtypes as cortex-led, normal-appearing white matter-led, and lesion-led. People with the lesion-led subtype have the highest risk of confirmed disability progression (CDP) and the highest relapse rate. People with the lesion-led MS subtype show positive treatment response in selected clinical trials. Our findings suggest that MRI-based subtypes predict MS disability progression and response to treatment and may be used to define groups of patients in interventional trials.

PubMed Disclaimer

Conflict of interest statement

A.E. has received speaker’s honoraria from Biogen and At The Limits educational programme. He has received travel support from the National Multiple Sclerosis Society and honorarium from the Journal of Neurology, Neurosurgy and Psychiatry for Editorial Commentaries. In the last 3 years D.C. has received honoraria from Excemed (2017) for faculty-led education work; had meeting expenses funded by the IMSCOGS (2019), EAN (2018), ECTRIMS (2018) and Société des Neurosciences (2017). He is a consultant for Biogen and Hoffmann-La Roche. He has received research funding from the International Progressive MS Alliance, the MS Society, and the National Institute for Health Research (NIHR) University College London Hospitals (UCLH) Biomedical Research Centre. He is a member of the MS Society’s Biomedical Grant Review Panel and a trustee of the MS Trust. O.C. has received research grants from the MS Society of Great Britain & Northern Ireland, National Institute for Health Research (NIHR) University College London Hospitals Biomedical Research Centre, EUH2020, Spinal Cord Research Foundation, and Rosetrees Trust. She serves as a consultant for Novartis, Teva, and Roche and has received an honorarium from the American Academy of Neurology as Associate Editor of Neurology and serves on the Editorial Board of Multiple Sclerosis Journal. CRGG has received research grants form Sanofi and the National Multiple Sclerosis Society. F.B. has received compensation for consulting services and/or speaking activities from Bayer Schering Pharma, Biogen Idec, Merck Serono, Novartis, Genzyme, Synthon BV, Roche, Teva, Jansen research and IXICO and is supported by the NIHR Biomedical Research Centre at UCLH. A.J.T. has received honoraria/support for travel for consultancy from Eisai, Hoffman La Roche, Almirall, and Excemed, and support for travel for consultancy as chair of the International Progressive MS Alliance Scientific Steering Committee, and from the National MS Society (USA) as a member of the Research Programs Advisory Committee. He receives an honorarium from SAGE Publishers as Editor-in-Chief of Multiple Sclerosis. Journal and a free subscription from Elsevier as a board member for the Lancet Neurology. D.L.A. has received research grant funding and/ or personal compensation for consulting from Acorda, Adelphi, Alkermes, Biogen, Celgene, Frequency Therapeutics, Genentech, Genzyme, Hoffman-La Roche, Immuene Tolerance Network, Immunotec, MedDay, EMD Serono, Novartis, Pfizer, Receptos, Roche, Sanofi-Aventis, Canadian Institutes of Health Research, MS Society of Canada, and International Progressive MS Alliance; and holds an equity interest in NeuroRx Research. F.B., D.C.A. and A.E. hold equity stake in Queen Square Analytics. S.N. has received research funding from the Canadian Institutes of Health Research, the International Progressive MS Alliance, the Myelin Repair Foundation and Immunotec. He has received honoraria/travel support from Genentech and MedDay, and personal compensation from NeuroRx Research. The remaining authors declare no competing interests.

Figures

Fig. 1
Fig. 1. MRI-based subtypes.
the evolution of MRI abnormalities in each of the three MRI-based subtypes. The colour shade ranges from blue to pink which represents the probability of abnormality (it can be interpreted as the degree of abnormality) (mild, moderate or severe which approximates 1, 2 and 3 sigma). The cortex-led subtype (left) showed cortical atrophy in the occipital, parietal and frontal cortex in the early stages of the sequences, and a reduction in T1/T2 ratio in the NAWM in the later stages. The normal-appearing white matter (NAWM)-led subtype (middle) showed a reduction in T1/T2 ratio of the cingulate bundle and corpus callosum in the earlier stages of the sequence, and deep grey matter and temporal grey matter atrophy in the later stages. The lesion-led subtype (right) shows early and extensive accumulation of lesions in the earlier stages of the sequence, and a reduction in the T1/T2 ratio in the NAWM in the later stages. The numbers on the left side represent SuStaIn stages. The minimum stage is 1 and the maximum stage is 39 (based on 13 variables that show mild (sigma = 1), moderate (sigma = 2) and severe abnormality (sigma = 3)). Acronyms: NAWM, normal-appearing white matter; SD, standard deviation; GM, grey matter; T1/T2, T1-T2 ratio.
Fig. 2
Fig. 2. Subtype membership in the training, and validation datasets.
a MRI-based subtypes in the training and internal validation dataset and b the validation dataset. Assignability of the disease subtype, or membership probability, is shown as the distance from each vertex of the triangle. Each of vertices represent the point at which membership of a given subtype is at its maximum (100%). We assigned each subject to one subtype (shown in red, green and blue) based on their maximum probability. c, d The 80th and 90th percentiles for the probability of assignment to the dominant subtype was 99.98% and 99.99% (indistinguishable in the figure) in the training dataset. In the validation dataset these percentiles were 99.45% and 99.97% respectively.
Fig. 3
Fig. 3. MRI-based subtypes and disability progression in the placebo arms.
The lesion-led subtype had a faster EDSS progression than the other two MS subtypes in both the training (a) and validation (b) sets. Only placebo arms (or comparator arms) of the clinical trials are included. In both a and b we used the log-rank test, with two-sided p-value, to compare survival curves (no correction for multiple comparisons). EDSS expanded disability status scale.
Fig. 4
Fig. 4. MRI-based subtypes predicted disease activity in the placebo arms of the validation dataset.
The average annual relapse rate for each MRI-based subtype. The centre shows the estimated average of annual relapse rate and error bars represent the standard error. The lesion-led subtype had significantly higher annual relapse rate than the cortex-led subtype (n = 1663 patients).
Fig. 5
Fig. 5. Stratification predicts disability progression.
Higher SuStaIn stage at baseline predicted time to disability progression: the higher the stage at baseline, the shorter the time to reach 24-week confirmed EDSS progression. p-Value is two-sided (p < 0.0001). When we repeated this analysis inside each MRI-based subtype we found similar results (results not shown). EDSS expanded disability status scale.
Fig. 6
Fig. 6. Predicting treatment response with MRI-based subtyping in selected RCTs.
Shows the change in EDSS worsening in MRI-based subtypes in the pooled treatment arms of the ORATORIO, ASCEND and OLYMPUS trials (n = 2099 patients) compared to the corresponding subtypes in the pooled placebo arms (e.g., lesion-led subtype on treatment vs. lesion led subtype on placebo and so forth). Patients in the lesion-led subtype had the largest reduction in the rate of EDSS worsening and were the only group who had a significant treatment response. The circle at the centre of each line represents the model-estimated average of percentage EDSS change. Error bars represent the standard error. Abbreviations: 9HPT, 9-Hole Peg test; NAMW, normal-appearing white matter; EDSS, Expanded Disability Status Scale; RRMS, relapsing-remitting multiple sclerosis; PPMS, primary progressive multiple sclerosis; RCT, randomised controlled trial.
Fig. 7
Fig. 7. Model development and validation.
We processed MRI with a uniform processing pipeline. We trained the model using 14 data sets, and applied the trained model on five independent, unseen data sets for validation. We demonstrated if MRI-based subtyping at baseline, could predict EDSS progression and disease activity. In selected RCTs, from RRMS and progressive (SP and PP MS), we looked at if MRI-based subtyping could predict treatment response. EDSS expanded disability status scale, RCT randomised controlled trial, Tx treatment, PASAT paced auditory serial addition test.
See this image and copyright information in PMC

References

    1. The Lancet. ICD-11: a brave attempt at classifying a new world. Lancet. 2018;391:2476. - PubMed
    1. Thompson AJ, Baranzini SE, Geurts J, Hemmer B, Ciccarelli O. Multiple sclerosis. Lancet. 2018;391:1622–1636. doi: 10.1016/S0140-6736(18)30481-1. - DOI - PubMed
    1. Lublin FD, et al. Defining the clinical course of multiple sclerosis: the 2013 revisions. Neurology. 2014;83:278–286. doi: 10.1212/WNL.0000000000000560. - DOI - PMC - PubMed
    1. Stys PK, Zamponi GW, van Minnen J, Geurts JJG. Will the real multiple sclerosis please stand up? Nat. Rev. Neurosci. 2012;13:507–514. doi: 10.1038/nrn3275. - DOI - PubMed
    1. Filippi M, et al. Association between pathological and MRI findings in multiple sclerosis. Lancet Neurol. 2019;18:198–210. doi: 10.1016/S1474-4422(18)30451-4. - DOI - PubMed

Publication types