Logo Logo
Help
Contact
Switch Language to German
Rozycki, Martin; Satterthwaite, Theodore D.; Koutsouleris, Nikolaos; Erus, Guray; Doshi, Jimit; Wolf, Daniel H.; Fan, Yong; Gur, Raquel E.; Gur, Ruben C.; Meisenzahl, Eva M.; Zhuo, Chuanjun; Ying, Hong; Yan, Hao; Yue, Weihua; Zhang, Dai; Davatzikos, Christos (2018): Multisite Machine Learning Analysis Provides a Robust Structural Imaging Signature of Schizophrenia Detectable Across Diverse Patient Populations and Within Individuals. In: Schizophrenia Bulletin, Vol. 44, No. 5: pp. 1035-1044
Full text not available from 'Open Access LMU'.

Abstract

Past work on relatively small, single-site studies using regional volumetry, and more recently machine learning methods, has shown that widespread structural brain abnormalities are prominent in schizophrenia. However, to be clinically useful, structural imaging biomarkers must integrate high-dimensional data and provide reproducible results across clinical populations and on an individual person basis. Using advanced multi-variate analysis tools and pooled data from case-control imaging studies conducted at 5 sites (941 adult participants, including 440 patients with schizophrenia), a neuroanatomical signature of patients with schizophrenia was found, and its robustness and reproducibility across sites, populations, and scanners, was established for single-patient classification. Analyses were conducted at multiple scales, including regional volumes, voxelwise measures, and complex distributed patterns. Single-subject classification was tested for single-site, pooled-site, and leave-site-out generalizability. Regional and voxelwise analyses revealed a pattern of widespread reduced regional gray matter volume, particularly in the medial prefrontal, temporolimbic and peri-Sylvian cortex, along with ventricular and pallidum enlargement. Multivariate classification using pooled data achieved a cross-validated prediction accuracy of 76% (AUC = 0.84). Critically, the leave-site-out validation of the detected schizophrenia signature showed accuracy/AUC range of 72-77%/0.73-0.91, suggesting a robust generalizability across sites and patient cohorts. Finally, individualized patient classifications displayed significant correlations with clinical measures of negative, but not positive, symptoms. Taken together, these results emphasize the potential for structural neuroimaging data to provide a robust and reproducible imaging signature of schizophrenia. A web-accessible portal is offered to allow the community to obtain individualized classifications of magnetic resonance imaging scans using the methods described herein.