{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T17:03:13Z","timestamp":1775840593979,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T00:00:00Z","timestamp":1560124800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T00:00:00Z","timestamp":1560124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000272","name":"DH | National Institute for Health Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000272","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Changes on brain imaging may precede clinical manifestations or disclose disease progression opaque to conventional clinical measures. Where, as in multiple sclerosis, the pathological process has a complex anatomical distribution, such changes are not easily detected by low-dimensional models in common use. This hinders our ability to detect treatment effects, both in the management of individual patients and in interventional trials. Here we compared the ability of conventional models to detect an imaging response to treatment against high-dimensional models incorporating a wide multiplicity of imaging factors. We used fully-automated image analysis to extract 144 regional, longitudinal trajectories of pre- and post- treatment changes in brain volume and disconnection in a cohort of 124 natalizumab-treated patients. Low- and high-dimensional models of the relationship between treatment and the trajectories of change were built and evaluated with machine learning, quantifying performance with receiver operating characteristic curves. Simulations of randomised controlled trials enrolling varying numbers of patients were used to quantify the impact of dimensionality on statistical efficiency. Compared to existing methods, high-dimensional models were superior in treatment response detection (area under the receiver operating characteristic curve\u2009=\u20090.890 [95% CI\u2009=\u20090.885\u20130.895] vs. 0.686 [95% CI\u2009=\u20090.679\u20130.693], <jats:italic>P<\/jats:italic>\u2009&lt;\u20090.01]) and in statistical efficiency (achieved statistical power\u2009=\u20090.806 [95% CI\u2009=\u20090.698\u20130.872] vs. 0.508 [95% CI\u2009=\u20090.403\u20130.593] with number of patients enrolled\u2009=\u200950, at <jats:italic>\u03b1<\/jats:italic>\u2009=\u20090.01). High-dimensional models based on routine, clinical imaging can substantially enhance the detection of the imaging response to treatment in multiple sclerosis, potentially enabling more accurate individual prediction and greater statistical efficiency of randomised controlled trials.<\/jats:p>","DOI":"10.1038\/s41746-019-0127-8","type":"journal-article","created":{"date-parts":[[2019,6,10]],"date-time":"2019-06-10T00:02:44Z","timestamp":1560124964000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["High-dimensional detection of imaging response to treatment in multiple sclerosis"],"prefix":"10.1038","volume":"2","author":[{"given":"Baris","family":"Kanber","sequence":"first","affiliation":[]},{"given":"Parashkev","family":"Nachev","sequence":"additional","affiliation":[]},{"given":"Frederik","family":"Barkhof","sequence":"additional","affiliation":[]},{"given":"Alberto","family":"Calvi","sequence":"additional","affiliation":[]},{"given":"Jorge","family":"Cardoso","sequence":"additional","affiliation":[]},{"given":"Rosa","family":"Cortese","sequence":"additional","affiliation":[]},{"given":"Ferran","family":"Prados","sequence":"additional","affiliation":[]},{"given":"Carole H.","family":"Sudre","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1849-3184","authenticated-orcid":false,"given":"Carmen","family":"Tur","sequence":"additional","affiliation":[]},{"given":"Sebastien","family":"Ourselin","sequence":"additional","affiliation":[]},{"given":"Olga","family":"Ciccarelli","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,6,10]]},"reference":[{"key":"127_CR1","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1017\/S1355617798466037","volume":"4","author":"PW Burgess","year":"1998","unstructured":"Burgess, P. W., Alderman, N., Evans, J., Emslie, H. & Wilson, B. A. The ecological validity of tests of executive function. Int. J. Neuropsychol. Soc. 4, 547\u2013558 (1998).","journal-title":"Int. J. Neuropsychol. Soc."},{"key":"127_CR2","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1002\/ana.25145","volume":"83","author":"A Eshaghi","year":"2018","unstructured":"Eshaghi, A. et al. Deep gray matter volume loss drives disability worsening in multiple sclerosis. Ann. Neurol. 83, 210\u2013222 (2018).","journal-title":"Ann. Neurol."},{"key":"127_CR3","first-page":"597","volume":"11","author":"MP Wattjes","year":"2015","unstructured":"Wattjes, M. P. et al. Evidence-based guidelines: MAGNIMS consensus guidelines on the use of MRI in multiple sclerosis\u2013establishing disease prognosis and monitoring patients. Nat. Rev. Neurol. 11, 597\u2013606 (2015).","journal-title":"Nat. Rev. Neurol."},{"key":"127_CR4","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1038\/nrneurol.2015.106","volume":"11","author":"\u00c0 Rovira","year":"2015","unstructured":"Rovira, \u00c0. et al. Evidence-based guidelines: MAGNIMS consensus guidelines on the use of MRI in multiple sclerosis\u2014clinical implementation in the diagnostic process. Nat. Rev. Neurol. 11, 471\u2013482 (2015).","journal-title":"Nat. Rev. Neurol."},{"key":"127_CR5","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1038\/nrneurol.2015.194","volume":"11","author":"C Enzinger","year":"2015","unstructured":"Enzinger, C. et al. Nonconventional MRI and microstructural cerebral changes in multiple sclerosis. Nat. Rev. Neurol. 11, 676\u2013686 (2015).","journal-title":"Nat. Rev. Neurol."},{"key":"127_CR6","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1093\/brain\/awv337","volume":"139","author":"MD Steenwijk","year":"2015","unstructured":"Steenwijk, M. D. et al. Cortical atrophy patterns in multiple sclerosis are non-random and clinically relevant. Brain 139, 115\u2013126 (2015).","journal-title":"Brain"},{"key":"127_CR7","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1093\/brain\/awy088","volume":"141","author":"A Eshaghi","year":"2018","unstructured":"Eshaghi, A. et al. Progression of regional grey matter atrophy in multiple sclerosis. Brain 141, 1665\u20131677 (2018).","journal-title":"Brain"},{"key":"127_CR8","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1093\/brain\/awx288","volume":"141","author":"T Xu","year":"2018","unstructured":"Xu, T., Rolf J\u00e4ger, H., Husain, M., Rees, G. & Nachev, P. High-dimensional therapeutic inference in the focally damaged human brain. Brain 141, 48\u201354 (2018).","journal-title":"Brain"},{"key":"127_CR9","unstructured":"Yoo, Y. et al. Deep learning of brain lesion patterns and user-defined clinical and MRI features for predicting conversion to multiple sclerosis from clinically isolated syndrome. Comput. Methods Biomech. Biomed. Eng. Imaging Vis. 0, 1\u201310 (2017)."},{"key":"127_CR10","first-page":"86","volume-title":"Deep Learning and Data Labeling for Medical Applications","author":"Youngjin Yoo","year":"2016","unstructured":"Yoo, Y. et al. Deep learning of brain lesion patterns for predicting future disease activity in patients with early symptoms of multiple sclerosis. In Deep Learning and Data Labeling for Medical Applications (eds Carneiro, G. et al.) 86\u201394 (Springer International Publishing, Cham, Switzerland, 2016)."},{"key":"127_CR11","doi-asserted-by":"crossref","unstructured":"Doyle, A., Precup, D., Arnold, D. L. & Arbel, T. Predicting future disease activity and treatment responders for multiple sclerosis patients using a bag-of-lesions brain representation. In Medical Image Computing and Computer-Assisted Intervention (eds Descoteaux, M. et al.) 186\u2013194 (Springer International Publishing, Cham, Switzerland, 2017).","DOI":"10.1007\/978-3-319-66179-7_22"},{"key":"127_CR12","doi-asserted-by":"crossref","unstructured":"Brosch, T., Yoo, Y., Li, D. K. B., Traboulsee, A. & Tam, R. Modeling the variability in brain morphology and lesion distribution in multiple sclerosis by deep learning. in Medical Image Computing and Computer-Assisted Intervention (eds Golland, P., Hata, N., Barillot, C., Hornegger, J. & Howe, R.) 462\u2013469 (Springer International Publishing, Cham, Switzerland, 2014).","DOI":"10.1007\/978-3-319-10470-6_58"},{"key":"127_CR13","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1177\/1352458514556300","volume":"21","author":"J Sastre-Garriga","year":"2015","unstructured":"Sastre-Garriga, J. et al. Brain atrophy in natalizumab-treated patients: a 3-year follow-up. Mult. Scler. 21, 749\u2013756 (2015).","journal-title":"Mult. Scler."},{"key":"127_CR14","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/S1474-4422(12)70003-0","volume":"11","author":"M Filippi","year":"2012","unstructured":"Filippi, M. et al. Association between pathological and MRI findings in multiple sclerosis. Lancet Neurol. 11, 349\u2013360 (2012).","journal-title":"Lancet Neurol."},{"key":"127_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40893-017-0033-3","volume":"3","author":"A Favaretto","year":"2018","unstructured":"Favaretto, A., Lazzarotto, A., Margoni, M., Poggiali, D. & Gallo, P. Effects of disease modifying therapies on brain and grey matter atrophy in relapsing remitting multiple sclerosis. Mult. Scler. Demyelinating Disord. 3, 1 (2018).","journal-title":"Mult. Scler. Demyelinating Disord."},{"key":"127_CR16","doi-asserted-by":"publisher","first-page":"1175","DOI":"10.1177\/1352458512473190","volume":"19","author":"A Vidal-Jordana","year":"2013","unstructured":"Vidal-Jordana, A. et al. Early brain pseudoatrophy while on natalizumab therapy is due to white matter volume changes. Mult. Scler. 19, 1175\u20131181 (2013).","journal-title":"Mult. Scler."},{"key":"127_CR17","unstructured":"Kanber, B. et al. An integrated imaging informatics software platform to improve the analysis of clinical trials and research data in MS. In Proc. 32nd Congress of the European Committee for Treatment and Research in Multiple Sclerosis Vol. 22, 229\u2013230 (London, England, 2016)."},{"key":"127_CR18","doi-asserted-by":"publisher","first-page":"1976","DOI":"10.1109\/TMI.2015.2418298","volume":"34","author":"MJ Cardoso","year":"2015","unstructured":"Cardoso, M. J. et al. Geodesic information flows: spatially-variant graphs and their application to segmentation and fusion. IEEE Trans. Med. Imaging 34, 1976\u20131988 (2015).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"127_CR19","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/s12021-017-9348-7","volume":"16","author":"\u017d Lesjak","year":"2018","unstructured":"Lesjak, \u017d. et al. A nNovel public MR image dataset of multiple sclerosis Patients with lesion segmentations based on multi-rater consensus. Neuroinformatics 16, 51\u201363 (2018).","journal-title":"Neuroinformatics"},{"key":"127_CR20","doi-asserted-by":"publisher","first-page":"145007","DOI":"10.1088\/1361-6560\/aacb65","volume":"63","author":"JP Kieselmann","year":"2018","unstructured":"Kieselmann, J. P. et al. Geometric and dosimetric evaluations of atlas-based segmentation methods of MR images in the head and neck region. Phys. Med. Biol. 63, 145007 (2018).","journal-title":"Phys. Med. Biol."},{"key":"127_CR21","unstructured":"Prados, F. et al. Multi-contrast patchmatch algorithm for multiple sclerosis lesion detection. In: ISBI 2015 \u2013 Longitudinal MS Lesion Segmentation Challenge. pp. 1\u20132 (2015). https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC5344762\/."},{"key":"127_CR22","doi-asserted-by":"publisher","first-page":"2079","DOI":"10.1109\/TMI.2015.2419072","volume":"34","author":"CH Sudre","year":"2015","unstructured":"Sudre, C. H. et al. Bayesian model selection for pathological neuroimaging data applied to white matter lesion segmentation. IEEE Trans. Med. Imaging 34, 2079\u20132102 (2015).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"127_CR23","doi-asserted-by":"publisher","first-page":"1245","DOI":"10.1038\/nn.2905","volume":"14","author":"M Thiebaut de Schotten","year":"2011","unstructured":"Thiebaut de Schotten, M. et al. A lateralized brain network for visuospatial attention. Nat. Neurosci. 14, 1245\u20131246 (2011).","journal-title":"Nat. Neurosci."},{"key":"127_CR24","doi-asserted-by":"publisher","first-page":"4812","DOI":"10.1093\/cercor\/bhv173","volume":"25","author":"M Thiebaut de Schotten","year":"2015","unstructured":"Thiebaut de Schotten, M. et al. From Phineas Gage and Monsieur Leborgne to H.M.: revisiting disconnection syndromes. Cereb. Cortex 25, 4812\u20134827 (2015).","journal-title":"Cereb. Cortex"},{"key":"127_CR25","doi-asserted-by":"publisher","first-page":"1751","DOI":"10.1007\/s00429-015-1001-3","volume":"221","author":"K Rojkova","year":"2016","unstructured":"Rojkova, K. et al. Atlasing the frontal lobe connections and their variability due to age and education: a spherical deconvolution tractography study. Brain Struct. Funct. 221, 1751\u20131766 (2016).","journal-title":"Brain Struct. Funct."},{"key":"127_CR26","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giy004","volume":"7","author":"C Foulon","year":"2018","unstructured":"Foulon, C. et al. Advanced lesion symptom mapping analyses and implementation as BCBtoolkit. GigaScience 7, giy004 (2018).","journal-title":"GigaScience"},{"key":"127_CR27","unstructured":"Makalic, E. & Schmidt, D. F. High-dimensional Bayesian regularised regression with the BayesReg Package. Preprint at arXiv (2016). https:\/\/arxiv.org\/abs\/1611.06649."},{"key":"127_CR28","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1214\/ss\/1042727942","volume":"17","author":"PR Rosenbaum","year":"2002","unstructured":"Rosenbaum, P. R. Covariance adjustment in randomized experiments and observational studies. Stat. Sci. 17, 286\u2013327 (2002).","journal-title":"Stat. Sci."},{"key":"127_CR29","doi-asserted-by":"publisher","unstructured":"Snoek, L., Mileti\u0107, S. & Scholte, H. S. How to control for confounds in decoding analyses of neuroimaging data. bioRxiv 290684 (2018). https:\/\/doi.org\/10.1101\/290684.","DOI":"10.1101\/290684"},{"key":"127_CR30","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1515\/ijb-2015-0030","volume":"12","author":"KA Linn","year":"2016","unstructured":"Linn, K. A., Gaonkar, B., Doshi, J., Davatzikos, C. & Shinohara, R. T. Addressing confounding in predictive models with an application to neuroimaging. Int. J. Biostat. 12, 31\u201344 (2016).","journal-title":"Int. J. Biostat."},{"key":"127_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang, C.-C. & Lin, C.-J. LIBSVM: A Library for Support Vector Machines. ACM Trans. Intell. Syst. Technol. 2, 1\u201327 (2011).","journal-title":"ACM Trans. Intell. Syst. Technol."},{"key":"127_CR32","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"P Geurts","year":"2006","unstructured":"Geurts, P., Ernst, D. & Wehenkel, L. Extremely randomized trees. Mach. Learn. 63, 3\u201342 (2006).","journal-title":"Mach. Learn."},{"key":"127_CR33","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F. et al. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011).","journal-title":"J. Mach. Learn. Res."},{"key":"127_CR34","doi-asserted-by":"publisher","first-page":"175","DOI":"10.3758\/BF03193146","volume":"39","author":"F Faul","year":"2007","unstructured":"Faul, F., Erdfelder, E., Lang, A.-G. & Buchner, A. G*Power 3: a flexible statistical power analysis program for the social, behavioral, and biomedical sciences. Behav. Res. Methods 39, 175\u2013191 (2007).","journal-title":"Behav. Res. Methods"}],"updated-by":[{"DOI":"10.1038\/s41746-019-0144-7","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2019,7,16]],"date-time":"2019-07-16T00:00:00Z","timestamp":1563235200000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0127-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0127-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0127-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,17]],"date-time":"2022-12-17T18:28:31Z","timestamp":1671301711000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-019-0127-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,10]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2019,12]]}},"alternative-id":["127"],"URL":"https:\/\/doi.org\/10.1038\/s41746-019-0127-8","relation":{"correction":[{"id-type":"doi","id":"10.1038\/s41746-019-0144-7","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,10]]},"assertion":[{"value":"12 February 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 July 2019","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"An amendment to this paper has been published and can be accessed via a link at the top of the paper.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"O.C. and F.B. are consultants for Biogen which manufactures the drug taken by the patients included into the study. However, Biogen did not sponsor the study and patients were seen as per routine clinical care. The remaining authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"49"}}