Stratification of multiple sclerosis patients using unsupervised machine learning: a single-visit MRI-driven approach.
Brain
Machine learning
Magnetic resonance imaging
Multiple sclerosis
Prognosis
Journal
European radiology
ISSN: 1432-1084
Titre abrégé: Eur Radiol
Pays: Germany
ID NLM: 9114774
Informations de publication
Date de publication:
Aug 2022
Aug 2022
Historique:
received:
16
11
2021
accepted:
23
01
2022
revised:
30
12
2021
pubmed:
15
3
2022
medline:
16
7
2022
entrez:
14
3
2022
Statut:
ppublish
Résumé
To stratify patients with multiple sclerosis (pwMS) based on brain MRI-derived volumetric features using unsupervised machine learning. The 3-T brain MRIs of relapsing-remitting pwMS including 3D-T1w and FLAIR-T2w sequences were retrospectively collected, along with Expanded Disability Status Scale (EDSS) scores and long-term (10 ± 2 years) clinical outcomes (EDSS, cognition, and progressive course). From the MRIs, volumes of demyelinating lesions and 116 atlas-defined gray matter regions were automatically segmented and expressed as z-scores referenced to external populations. Following feature selection, baseline MRI-derived biomarkers entered the Subtype and Stage Inference (SuStaIn) algorithm, which estimates subgroups characterized by distinct patterns of biomarker evolution and stages within subgroups. The trained model was then applied to longitudinal MRIs. Stability of subtypes and stage change over time were assessed via Krippendorf's α and multilevel linear regression models, respectively. The prognostic relevance of SuStaIn classification was assessed with ordinal/logistic regression analyses. We selected 425 pwMS (35.9 ± 9.9 years; F/M: 301/124), corresponding to 1129 MRI scans, along with healthy controls (N = 148; 35.9 ± 13.0 years; F/M: 77/71) and external pwMS (N = 80; 40.4 ± 11.9 years; F/M: 56/24) as reference populations. Based on 11 biomarkers surviving feature selection, two subtypes were identified, designated as "deep gray matter (DGM)-first" subtype (N = 238) and "cortex-first" subtype (N = 187) according to the atrophy pattern. Subtypes were consistent over time (α = 0.806), with significant annual stage increase (b = 0.20; p < 0.001). EDSS was associated with stage and DGM-first subtype (p ≤ 0.02). Baseline stage predicted long-term disability, transition to progressive course, and cognitive impairment (p ≤ 0.03), with the latter also associated with DGM-first subtype (p = 0.005). Unsupervised learning modelling of brain MRI-derived volumetric features provides a biologically reliable and prognostically meaningful stratification of pwMS. • The unsupervised modelling of brain MRI-derived volumetric features can provide a single-visit stratification of multiple sclerosis patients. • The so-obtained classification tends to be consistent over time and captures disease-related brain damage progression, supporting the biological reliability of the model. • Baseline stratification predicts long-term clinical disability, cognition, and transition to secondary progressive course.
Identifiants
pubmed: 35284989
doi: 10.1007/s00330-022-08610-z
pii: 10.1007/s00330-022-08610-z
pmc: PMC9279232
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
5382-5391Informations de copyright
© 2022. The Author(s).
Références
Filippi M, Brück W, Chard D et al (2019) Association between pathological and MRI findings in multiple sclerosis. Lancet Neurol 18:198–210
doi: 10.1016/S1474-4422(18)30451-4
Vermersch P, Berger T, Gold R et al (2016) The clinical perspective: how to personalise treatment in MS and how may biomarkers including imaging contribute to this? Mult Scler 22:18–33
doi: 10.1177/1352458516650739
Traboulsee A, Simon JH, Stone L et al (2016) Revised recommendations of the Consortium of MS Centers Task Force for a standardized mri protocol and clinical guidelines for the diagnosis and follow-up of multiple sclerosis. AJNR Am J Neuroradiol 37:394–401
doi: 10.3174/ajnr.A4539
Wattjes MP, Rovira A, Miller D et al (2015) Evidence-based guidelines: MAGNIMS consensus guidelines on the use of MRI in multiple sclerosis--establishing disease prognosis and monitoring patients. Nat Rev Neurol 11:597–606
pubmed: 26369511
Pontillo G, Cocozza S, Di Stasi M et al (2020) 2D linear measures of ventricular enlargement may be relevant markers of brain atrophy and long-term disability progression in multiple sclerosis. Eur Radiol 30:3813–3822
doi: 10.1007/s00330-020-06738-4
Young AL, Oxtoby NP, Daga P et al (2014) A data-driven model of biomarker changes in sporadic Alzheimer's disease. Brain 137:2564–2577
doi: 10.1093/brain/awu176
Fonteijn HM, Modat M, Clarkson MJ et al (2012) An event-based model for disease progression and its application in familial Alzheimer's disease and Huntington's disease. Neuroimage 60:1880–1889
doi: 10.1016/j.neuroimage.2012.01.062
Young AL, Marinescu RV, Oxtoby NP et al (2018) Uncovering the heterogeneity and temporal complexity of neurodegenerative diseases with Subtype and Stage Inference. Nat Commun 9:4273
doi: 10.1038/s41467-018-05892-0
Eshaghi A, Marinescu RV, Young AL et al (2018) Progression of regional grey matter atrophy in multiple sclerosis. Brain 141:1665–1677
doi: 10.1093/brain/awy088
Dekker I, Schoonheim MM, Venkatraghavan V et al (2021) The sequence of structural, functional and cognitive changes in multiple sclerosis. Neuroimage Clin 29:102550
doi: 10.1016/j.nicl.2020.102550
Eshaghi A, Young AL, Wijeratne PA et al (2021) Identifying multiple sclerosis subtypes using unsupervised machine learning and MRI data. Nat Commun 12:2078
doi: 10.1038/s41467-021-22265-2
Polman CH, Reingold SC, Banwell B et al (2011) Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria. Ann Neurol 69:292–302
doi: 10.1002/ana.22366
Lublin FD, Reingold SC, Cohen JA et al (2014) Defining the clinical course of multiple sclerosis: the 2013 revisions. Neurology 83:278–286
doi: 10.1212/WNL.0000000000000560
Confavreux C, Vukusic S (2006) Age at disability milestones in multiple sclerosis. Brain 129:595–605
doi: 10.1093/brain/awh714
Goretti B, Niccolai C, Hakiki B et al (2014) The Brief International Cognitive Assessment for Multiple Sclerosis (BICAMS): normative values with gender, age and education corrections in the Italian population. BMC Neurol 14:171
doi: 10.1186/s12883-014-0171-6
Benedict RH, Amato MP, Boringa J et al (2012) Brief International Cognitive Assessment for MS (BICAMS): international standards for validation. BMC Neurol 12:55
doi: 10.1186/1471-2377-12-55
Tzourio-Mazoyer N, Landeau B, Papathanassiou D et al (2002) Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15:273–289
doi: 10.1006/nimg.2001.0978
Hayes AF, Krippendorff K (2007) Answering the call for a standard reliability measure for coding data. Communication Methods and Measures 1:77–89
doi: 10.1080/19312450709336664
Gibbs RM, Lipnick S, Bateman JW et al (2018) Toward precision medicine for neurological and neuropsychiatric disorders. Cell Stem Cell 23:21–24
doi: 10.1016/j.stem.2018.05.019
Pontillo G, Cocozza S, Lanzillo R et al (2019) Determinants of deep gray matter atrophy in multiple sclerosis: a multimodal MRI study. AJNR Am J Neuroradiol 40:99–106
doi: 10.3174/ajnr.A5915
Calabrese M, Magliozzi R, Ciccarelli O, Geurts JJG, Reynolds R, Martin R (2015) Exploring the origins of grey matter damage in multiple sclerosis. Nature Reviews Neuroscience 16:147–158
doi: 10.1038/nrn3900
Geurts JJ, Barkhof F (2008) Grey matter pathology in multiple sclerosis. Lancet Neurol 7:841–851
doi: 10.1016/S1474-4422(08)70191-1
Ruggieri S, Petracca M, Miller A et al (2015) Association of deep gray matter damage with cortical and spinal cord degeneration in primary progressive multiple sclerosis. JAMA Neurol 72:1466–1474
doi: 10.1001/jamaneurol.2015.1897
Wijnands JMA, Kingwell E, Zhu F et al (2017) Health-care use before a first demyelinating event suggestive of a multiple sclerosis prodrome: a matched cohort study. Lancet Neurol 16:445–451
doi: 10.1016/S1474-4422(17)30076-5
Pagani E, Rocca MA, Gallo A et al (2005) Regional brain atrophy evolves differently in patients with multiple sclerosis according to clinical phenotype. AJNR Am J Neuroradiol 26:341–346
pubmed: 15709132
pmcid: 7974082
Fisher E, Lee JC, Nakamura K, Rudick RA (2008) Gray matter atrophy in multiple sclerosis: a longitudinal study. Ann Neurol 64:255–265
doi: 10.1002/ana.21436
Eshaghi A, Prados F, Brownlee WJ et al (2018) Deep gray matter volume loss drives disability worsening in multiple sclerosis. Ann Neurol 83:210–222
doi: 10.1002/ana.25145
Minagar A, Barnett MH, Benedict RH et al (2013) The thalamus and multiple sclerosis: modern views on pathologic, imaging, and clinical aspects. Neurology 80:210–219
doi: 10.1212/WNL.0b013e31827b910b
Houtchens MK, Benedict RH, Killiany R et al (2007) Thalamic atrophy and cognition in multiple sclerosis. Neurology 69:1213–1223
doi: 10.1212/01.wnl.0000276992.17011.b5
Petracca M, Pontillo G, Moccia M et al (2021) Neuroimaging correlates of cognitive dysfunction in adults with multiple sclerosis. Brain Sci 11:346
doi: 10.3390/brainsci11030346
Pontillo G, Petracca M, Monti S et al (2021) Unraveling deep gray matter atrophy and iron and myelin changes in multiple sclerosis. AJNR Am J Neuroradiol. https://doi.org/10.3174/ajnr.A7093
Cocozza S, Pontillo G, Russo C et al (2018) Cerebellum and cognition in progressive MS patients: functional changes beyond atrophy? J Neurol 265:2260–2266
doi: 10.1007/s00415-018-8985-6