Premium
Predicting the risk of psychosis onset: advances and prospects
Author(s) -
Strobl Eric V.,
Eack Shaun M.,
Swaminathan Vaidy,
Visweswaran Shyam
Publication year - 2012
Publication title -
early intervention in psychiatry
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.087
H-Index - 45
eISSN - 1751-7893
pISSN - 1751-7885
DOI - 10.1111/j.1751-7893.2012.00383.x
Subject(s) - psychosis , support vector machine , schizophrenia (object oriented programming) , machine learning , feature selection , psychology , artificial intelligence , quality of life (healthcare) , clinical psychology , computer science , psychiatry , psychotherapist
Aim To conduct a systematic review of the methods and performance characteristics of models developed for predicting the onset of psychosis. Methods We performed a comprehensive literature search restricted to E nglish articles and identified using P ub M ed, Medline and PsychI NFO , as well as the reference lists of published studies and reviews. Inclusion criteria included the selection of more than one variable to predict psychosis or schizophrenia onset, and selection of individuals at familial risk or clinical high risk. Eighteen studies met these criteria, and we compared these studies based on the subjects selected, predictor variables used and the choice of statistical or machine learning methods. Results Quality of life and life functioning as well as structural brain imaging emerged as the most promising predictors of psychosis onset, particularly when they were coupled with appropriate dimensionality reduction methods and predictive model algorithms like the support vector machine ( SVM ). Balanced accuracy ranged from 100% to 78% in four studies using the SVM , and 67% to 81% in 14 studies using general linear models. Conclusions Performance of the predictive models improves with quality of life measures, life functioning measures, structural brain imaging data, as well as with the use of methods like SVM . Despite these advances, the overall performance of psychosis predictive models is still modest. In the future, performance can potentially be improved by including genetic variant and new functional imaging data in addition to the predictors that are used currently.