Improved individualized prediction of schizophrenia in subjects at familial high risk, based on neuroanatomical data, schizotypal and neurocognitive features

• Published in: Schizophrenia research 2017-03, Vol.181, p.6-12
• Main Authors: Zarogianni, Eleni, Storkey, Amos J, Johnstone, Eve C, Owens, David G.C, Lawrie, Stephen M
• Format: Article
• Language: English
• Subjects: Adolescent; Adult; Brain - diagnostic imaging; Cognition; Diagnosis, Computer-Assisted; Familial HR; Family; Feasibility Studies; Female; Follow-Up Studies; Genetic Predisposition to Disease; Humans; Longitudinal Studies; Machine learning; Magnetic Resonance Imaging; Male; Memory; MRI; Multivariate Analysis; Neuropsychological Tests; Prediction; Psychiatry; Recursive feature elimination; Schizophrenia; Schizophrenia - classification; Schizophrenia - diagnosis; Schizophrenia - genetics; Schizophrenic Psychology; Schizotypal Personality Disorder - psychology; Support Vector Machine; Young Adult
• ISSN: 0920-9964; 1573-2509
• DOI: 10.1016/j.schres.2016.08.027

Abstract To date, there are no reliable markers for predicting onset of schizophrenia in individuals at high risk (HR). Substantial promise is, however, shown by a variety of pattern classification approaches to neuroimaging data. Here, we examined the predictive accuracy of support vector machine (SVM) in later diagnosing schizophrenia, at a single-subject level, using a cohort of HR individuals drawn from multiply affected families and a combination of neuroanatomical, schizotypal and neurocognitive variables. Baseline structural magnetic resonance imaging (MRI), schizotypal and neurocognitive data from 17 HR subjects, who subsequently developed schizophrenia and a matched group of 17 HR subjects who did not make the transition, yet had psychotic symptoms, were included in the analysis. We employed recursive feature elimination (RFE), in a nested cross-validation scheme to identify the most significant predictors of disease transition and enhance diagnostic performance. Classification accuracy was 94% when a self-completed measure of schizotypy, a declarative memory test and structural MRI data were combined into a single learning algorithm; higher than when either quantitative measure was used alone. The discriminative neuroanatomical pattern involved gray matter volume differences in frontal, orbito-frontal and occipital lobe regions bilaterally as well as parts of the superior, medial temporal lobe and cerebellar regions. Our findings suggest that an early SVM-based prediction of schizophrenia is possible and can be improved by combining schizotypal and neurocognitive features with neuroanatomical variables. However, our predictive model needs to be tested by classifying a new, independent HR cohort in order to estimate its validity.