BACKGROUND: Early diagnosis of schizophrenia could improve the outcome of the illness. Unlike classical between-group comparisons, machine learning can identify subtle disease patterns on a single subject level, which could help realize the potential of MRI in establishing a psychiatric diagnosis. Machine learning has previously been predominantly tested on gray-matter structural or functional MRI data. In this paper we used a machine learning classifier to differentiate patients with a first episode of schizophrenia-spectrum disorder (FES) from healthy controls using diffusion tensor imaging. METHODS: We applied linear support-vector machine (SVM) and traditional tract based spatial statistics between group analyses to brain fractional anisotropy (FA) data from 77 FES and 77 age and sex matched healthy controls. We also evaluated the effects of medication and symptoms on the SVM classification. RESULTS: The SVM distinguished between patients and controls with significant accuracy of 62.34% (p = 0.005). Participants with FES showed widespread FA reductions relative to controls in a large cluster (N = 56,647 voxels, corrected p = 0.002). The white matter regions, which contributed to the correct identification of participants with FES, overlapped with the regions, which showed lower FA in patients relative to controls. There was no association between the classification performance and medication or symptoms. CONCLUSIONS: Our results provide a proof of concept that SVM might help differentiate FES patients early in the course of illness from healthy controls using white-matter fractional anisotropy. As there was no effect of medications or symptoms, the SVM classification seemed to be based on trait rather than state markers and appeared to capture the lower FA in FES participants relative to controls.

3rd Faculty of Medicine Charles University Ruska 87 100 00 Prague Czech Republic

Department of Psychiatry and Psychotherapy Otto von Guericke University Leipziger Str 44 39120 Magdeburg Germany

Department of Psychiatry Dalhousie University QEII HSC A J Lane Bldg Room 3093 5909 Veteran's Memorial Lane Halifax NS B3H 2E2 Canada

Faculty of Nuclear Sciences and Physical Engineering Czech Technical University Prague Prague Brehova 78 7 110 00 Praha Czech Republic

Institute of Computer Science of the Czech Academy of Sciences Pod Vodarenskou vezi 271 2 182 07 Prague Czech Republic

MR Unit Department of Diagnostic and Interventional Radiology Institute for Clinical and Experimental Medicine Videnska 1958 9 140 21 Prague Czech Republic

National Institute of Mental Health Topolova 748 250 67 Klecany Czech Republic

Zobrazit více v PubMed

Whiteford HA, Degenhardt L, Rehm J, Baxter AJ, Ferrari AJ, Erskine HE, et al. Global burden of disease attributable to mental and substance use disorders: findings from the global burden of disease study 2010. Lancet Lond Engl. 2013;382:1575–1586. doi: 10.1016/S0140-6736(13)61611-6. PubMed DOI

Gustavsson A, Svensson M, Jacobi F, Allgulander C, Alonso J, Beghi E, et al. Cost of disorders of the brain in Europe 2010. Eur Neuropsychopharmacol J Eur Coll Neuropsychopharmacol. 2011;21:718–779. doi: 10.1016/j.euroneuro.2011.08.008. PubMed DOI

Guo X, Li J, Wei Q, Fan X, Kennedy DN, Shen Y, et al. Duration of untreated psychosis is associated with temporal and occipitotemporal gray matter volume decrease in treatment naÔve schizophrenia. PLoS One. 2013;8:e83679. doi: 10.1371/journal.pone.0083679. PubMed DOI PMC

Mikolas P, Melicher T, Skoch A, Matejka M, Slovakova A, Bakstein E, et al. Connectivity of the anterior insula differentiates participants with first-episode schizophrenia spectrum disorders from controls: a machine-learning study. Psychol Med. 2016;46:2695–2704. doi: 10.1017/S0033291716000878. PubMed DOI

Penttilä M, Jääskeläinen E, Haapea M, Tanskanen P, Veijola J, Ridler K, et al. Association between duration of untreated psychosis and brain morphology in schizophrenia within the northern Finland 1966 birth cohort. Schizophr Res. 2010;123:145–152. doi: 10.1016/j.schres.2010.08.016. PubMed DOI

Kambeitz J, Kambeitz-Ilankovic L, Leucht S, Wood S, Davatzikos C, Malchow B, et al. Detecting neuroimaging biomarkers for schizophrenia: a meta-analysis of multivariate pattern recognition studies. Neuropsychopharmacol Off Publ Am Coll Neuropsychopharmacol. 2015;40:1742–1751. doi: 10.1038/npp.2015.22. PubMed DOI PMC

Pettersson-Yeo W, Benetti S, Marquand AF, Dell’acqua F, Williams SCR, Allen P, et al. Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level. Psychol Med. 2013;43:2547–2562. doi: 10.1017/S003329171300024X. PubMed DOI PMC

Doughty C, Wang J, Feng W, Hackney D, Pani E, Schlaug G. Detection and predictive value of fractional anisotropy changes of the corticospinal tract in the acute phase of a stroke. Stroke J Cereb Circ. 2016;47:1520–1526. doi: 10.1161/STROKEAHA.115.012088. PubMed DOI PMC

Jones DK, Knˆsche TR, Turner R. White matter integrity, fiber count, and other fallacies: the do’s and don’ts of diffusion MRI. NeuroImage. 2013;73:239–254. doi: 10.1016/j.neuroimage.2012.06.081. PubMed DOI

Melicher T, Horacek J, Hlinka J, Spaniel F, Tintera J, Ibrahim I, et al. White matter changes in first episode psychosis and their relation to the size of sample studied: a DTI study. Schizophr Res. 2015;162:22–28. doi: 10.1016/j.schres.2015.01.029. PubMed DOI

Samartzis L, Dima D, Fusar-Poli P, Kyriakopoulos M. White matter alterations in early stages of schizophrenia: a systematic review of diffusion tensor imaging studies. J Neuroimaging. 2014;24:101–110. doi: 10.1111/j.1552-6569.2012.00779.x. PubMed DOI

Yao L, Lui S, Liao Y, Du M-Y, Hu N, Thomas JA, et al. White matter deficits in first episode schizophrenia: an activation likelihood estimation meta-analysis. Prog Neuro-Psychopharmacol Biol Psychiatry. 2013;45:100–106. doi: 10.1016/j.pnpbp.2013.04.019. PubMed DOI

Nieuwenhuis M, van Haren NEM, Hulshoff Pol HE, Cahn W, Kahn RS, Schnack HG. Classification of schizophrenia patients and healthy controls from structural MRI scans in two large independent samples. NeuroImage. 2012;61:606–12. doi: 10.1016/j.neuroimage.2012.03.079. PubMed DOI

Lecrubier Y, Sheehan DV, Weiller E, Amorim P, Bonora I, Harnett Sheehan K, et al. The MINI international neuropsychiatric interview (MINI). A short diagnostic structured interview: reliability and validity according to the CIDI. Eur Psychiatry. 1997;12:224–231. doi: 10.1016/S0924-9338(97)83296-8. DOI

Kay SR, Fiszbein A, Opler LA. The positive and negative syndrome scale (PANSS) for schizophrenia. Schizophr Bull. 1987;13:261–276. doi: 10.1093/schbul/13.2.261. PubMed DOI

Jenkinson M, Beckmann CF, Behrens TEJ, Woolrich MW, Smith SM. FSL. NeuroImage. 2012;62:782–790. doi: 10.1016/j.neuroimage.2011.09.015. PubMed DOI

Amarreh I, Meyerand ME, Stafstrom C, Hermann BP, Birn RM. Individual classification of children with epilepsy using support vector machine with multiple indices of diffusion tensor imaging. NeuroImage Clin. 2014;4:757–764. doi: 10.1016/j.nicl.2014.02.006. PubMed DOI PMC

Damoiseaux JS, RB RS a, Barkhof F, Scheltens P, Stam CJ, Smith SM, et al. Consistent resting-state networks across healthy subjects. Proc Natl Acad Sci. 2006;103:13848–13853. doi: 10.1073/pnas.0601417103. PubMed DOI PMC

Haller S, Lovblad K-O, Giannakopoulos P, Van De Ville D. Multivariate pattern recognition for diagnosis and prognosis in clinical neuroimaging: state of the art, current challenges and future trends. Brain Topogr. 2014;27:329–337. doi: 10.1007/s10548-014-0360-z. PubMed DOI

Haller S, Badoud S, Nguyen D, Garibotto V, Lovblad KO, Burkhard PR. Individual detection of patients with Parkinson disease using support vector machine analysis of diffusion tensor imaging data: initial results. AJNR Am J Neuroradiol. 2012;33:2123–2128. doi: 10.3174/ajnr.A3126. PubMed DOI PMC

Smith SM, Jenkinson M, Woolrich MW, Beckmann CF, Behrens TEJ, Johansen-Berg H, et al. Advances in functional and structural MR image analysis and implementation as FSL. NeuroImage. 2004;23(Suppl 1):S208–S219. doi: 10.1016/j.neuroimage.2004.07.051. PubMed DOI

Wu M-J, Mwangi B, Bauer IE, Passos IC, Sanches M, Zunta-Soares GB, et al. Identification and individualized prediction of clinical phenotypes in bipolar disorders using neurocognitive data, neuroimaging scans and machine learning. NeuroImage. 2017;145:254–64. PubMed PMC

Jenkinson M, Smith S. A global optimisation method for robust affine registration of brain images. Med Image Anal. 2001;5:143–156. doi: 10.1016/S1361-8415(01)00036-6. PubMed DOI

Schrouff J, Rosa MJ, Rondina JM, Marquand AF, Chu C, Ashburner J, et al. PRoNTo: pattern recognition for neuroimaging toolbox. Neuroinformatics. 2013;11:319–337. doi: 10.1007/s12021-013-9178-1. PubMed DOI PMC

LaConte S, Strother S, Cherkassky V, Anderson J, Hu X. Support vector machines for temporal classification of block design fMRI data. NeuroImage. 2005;26:317–329. doi: 10.1016/j.neuroimage.2005.01.048. PubMed DOI

Mourao-Miranda J, Reinders AA, Rocha-Rego V, Lappin J, Rondina J, Morgan C, et al. Individualized prediction of illness course at the first psychotic episode: a support vector machine MRI study. Psychol Med. 2012;42:1037–1047. doi: 10.1017/S0033291711002005. PubMed DOI PMC

Hajek T, Cooke C, Kopecek M, Novak T, Hoschl C, Alda M. Using structural MRI to identify individuals at genetic risk for bipolar disorders: a 2-cohort, machine learning study. J Psychiatry Neurosci JPN. 2015;40:316–324. doi: 10.1503/jpn.140142. PubMed DOI PMC

Rocha-Rego V, Jogia J, Marquand AF, Mourao-Miranda J, Simmons A, Frangou S. Examination of the predictive value of structural magnetic resonance scans in bipolar disorder: a pattern classification approach. Psychol Med. 2014;44:519–532. doi: 10.1017/S0033291713001013. PubMed DOI PMC

Franke K, Ziegler G, Klöppel S, Gaser C. Estimating the age of healthy subjects from T1-weighted MRI scans using kernel methods: exploring the influence of various parameters. NeuroImage. 2010;50:883–892. doi: 10.1016/j.neuroimage.2010.01.005. PubMed DOI

Platt JC. Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods. Adv large margin Classif. 1999:61–74.

Shawe-Taylor J, Cristianini N. Kernel methods for pattern analysis. 3rd printing. Cambridge: Cambridge University Press; 2006.

Nichols TE, Holmes AP. Nonparametric permutation tests for functional neuroimaging: a primer with examples. Hum Brain Mapp. 2002;15:1–25. doi: 10.1002/hbm.1058. PubMed DOI PMC

Winkler AM, Ridgway GR, Webster MA, Smith SM, Nichols TE. Permutation inference for the general linear model. NeuroImage. 2014;92:381–397. doi: 10.1016/j.neuroimage.2014.01.060. PubMed DOI PMC

Smith SM, Jenkinson M, Johansen-Berg H, Rueckert D, Nichols TE, Mackay CE, et al. Tract-based spatial statistics: voxelwise analysis of multi-subject diffusion data. NeuroImage. 2006;31:1487–1505. doi: 10.1016/j.neuroimage.2006.02.024. PubMed DOI

Ingalhalikar M, Kanterakis S, Gur R, Roberts TPL, Verma R. DTI based diagnostic prediction of a disease via pattern classification. Med Image Comput Comput-Assist Interv. 2010;13:558–565. PubMed

Sui J, He H, Yu Q, Chen J, Rogers J, Pearlson GD, et al. Combination of resting state fMRI, DTI, and sMRI data to discriminate schizophrenia by N-way MCCA + jICA. Front Hum Neurosci. 2013;7:235. doi: 10.3389/fnhum.2013.00235. PubMed DOI PMC

Alvarado-Alanis P, León-Ortiz P, Reyes-Madrigal F, Favila R, Rodríguez-Mayoral O, Nicolini H, et al. Abnormal white matter integrity in antipsychotic-naïve first-episode psychosis patients assessed by a DTI principal component analysis. Schizophr Res. 2015;162:14–21. doi: 10.1016/j.schres.2015.01.019. PubMed DOI PMC

Bora E, Fornito A, Radua J, Walterfang M, Seal M, Wood SJ, et al. Neuroanatomical abnormalities in schizophrenia: a multimodal voxelwise meta-analysis and meta-regression analysis. Schizophr Res. 2011;127:46–57. doi: 10.1016/j.schres.2010.12.020. PubMed DOI

Kanaan R, Barker G, Brammer M, Giampietro V, Shergill S, Woolley J, et al. White matter microstructure in schizophrenia: effects of disorder, duration and medication. Br J Psychiatry. 2009;194:236–242. doi: 10.1192/bjp.bp.108.054320. PubMed DOI PMC

Arbabshirani MR, Castro E, Calhoun VD. Accurate classification of schizophrenia patients based on novel resting-state fMRI features. IEEE. 2014:6691–4. [cited 2016 Sep 29] Available from: http://ieeexplore.ieee.org/document/6945163/ PubMed

Salvador R, Radua J, Canales-Rodríguez EJ, Solanes A, Sarró S, Goikolea JM, et al. Evaluation of machine learning algorithms and structural features for optimal MRI-based diagnostic prediction in psychosis. PLoS One. 2017:12. [cited 2017 Nov 28]; Available from: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5398548/ PubMed PMC

Schnack HG, Nieuwenhuis M, van Haren NEM, Abramovic L, Scheewe TW, Brouwer RM, et al. Can structural MRI aid in clinical classification? A machine learning study in two independent samples of patients with schizophrenia, bipolar disorder and healthy subjects. NeuroImage. 2014;84:299–306. doi: 10.1016/j.neuroimage.2013.08.053. PubMed DOI