Individualized prediction of psychosis in subjects with an at-risk mental state

SCHIZOPHRENIA RESEARCH

卷:214

Article

Zarogianni, Eleni¹  Storkey, Amos J.²  Borgwardt, Stefan³  Smieskova, Renata³  Studerus, Erich⁴  Riecher-Rossler, Anita⁴  Lawrie, Stephen M.¹ 

[1] Univ Edinburgh, Royal Edinburgh Hosp, Sch Clin Sci, Div Psychiat, Kennedy Tower,Morningside Pk, Edinburgh EH10 5HF, Midlothian, Scotland

[2] Univ Edinburgh, Inst Adapt & Neural Computat, Edinburgh, Midlothian, Scotland

[3] Univ Basel, Dept Psychiat UPK, Basel, Switzerland

[4] Univ Basel, Ctr Gender Res & Early Detect, Psychiat Hosp, Basel, Switzerland

关键词: Early diagnosis;    Psychosis onset;    Magnetic resonance imaging;    Support vector machine;    At-risk mental state;   

DOI  :  10.1016/j.schres.2017.08.061

来源: Elsevier

【 摘 要 】

Early intervention strategies in psychosis would significantly benefit from the identification of reliable prognostic biomarkers. Pattern classification methods have shown the feasibility of an early diagnosis of psychosis onset both in clinical and familial high-risk populations. Here we were interested in replicating our previous classification findings using an independent cohort at clinical high risk for psychosis, drawn from the prospective FePsy (Fruherkennung von Psychosen) study. The same neuroanatomical-based pattern classification pipeline, consisting of a linear Support Vector Machine (SVM) and a Recursive Feature Selection (RFE) achieved 74% accuracy in predicting later onset of psychosis. The discriminative neuroanatomical pattern underlying this finding consisted of many brain areas across all four lobes and the cerebellum. These results provide proof-of-concept that the early diagnosis of psychosis is feasible using neuroanatomical-based pattern recognition. (C) 2017 Elsevier B.V. All rights reserved.

【 授权许可】

Free