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 English articles and identified using PubMed, Medline and PsychINFO, 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.
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 English articles and identified using PubMed, Medline and PsychINFO, 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.
Authors: Henrik Ryberg; Jiyan An; Samuel Darko; Jonathan Llyle Lustgarten; Matt Jaffa; Vanathi Gopalakrishnan; David Lacomis; Merit Cudkowicz; Robert Bowser Journal: Muscle Nerve Date: 2010-07 Impact factor: 3.217
Authors: Doron Gothelf; Fumiko Hoeft; Takefumi Ueno; Lisa Sugiura; Agatha D Lee; Paul Thompson; Allan L Reiss Journal: J Psychiatr Res Date: 2011-03 Impact factor: 4.791
Authors: G Paul Amminger; Miriam R Schäfer; Konstantinos Papageorgiou; Claudia M Klier; Sue M Cotton; Susan M Harrigan; Andrew Mackinnon; Patrick D McGorry; Gregor E Berger Journal: Arch Gen Psychiatry Date: 2010-02
Authors: Shaun M Eack; Konasale M R Prasad; Debra M Montrose; Dhruman D Goradia; Diana Dworakowski; Jean Miewald; Matcheri S Keshavan Journal: Prog Neuropsychopharmacol Biol Psychiatry Date: 2008-09-09 Impact factor: 5.067
Authors: Shane E McCarthy; Vladimir Makarov; George Kirov; Anjene M Addington; Jon McClellan; Seungtai Yoon; Diana O Perkins; Diane E Dickel; Mary Kusenda; Olga Krastoshevsky; Verena Krause; Ravinesh A Kumar; Detelina Grozeva; Dheeraj Malhotra; Tom Walsh; Elaine H Zackai; Paige Kaplan; Jaya Ganesh; Ian D Krantz; Nancy B Spinner; Patricia Roccanova; Abhishek Bhandari; Kevin Pavon; B Lakshmi; Anthony Leotta; Jude Kendall; Yoon-Ha Lee; Vladimir Vacic; Sydney Gary; Lilia M Iakoucheva; Timothy J Crow; Susan L Christian; Jeffrey A Lieberman; T Scott Stroup; Terho Lehtimäki; Kaija Puura; Chad Haldeman-Englert; Justin Pearl; Meredith Goodell; Virginia L Willour; Pamela Derosse; Jo Steele; Layla Kassem; Jessica Wolff; Nisha Chitkara; Francis J McMahon; Anil K Malhotra; James B Potash; Thomas G Schulze; Markus M Nöthen; Sven Cichon; Marcella Rietschel; Ellen Leibenluft; Vlad Kustanovich; Clara M Lajonchere; James S Sutcliffe; David Skuse; Michael Gill; Louise Gallagher; Nancy R Mendell; Nick Craddock; Michael J Owen; Michael C O'Donovan; Tamim H Shaikh; Ezra Susser; Lynn E Delisi; Patrick F Sullivan; Curtis K Deutsch; Judith Rapoport; Deborah L Levy; Mary-Claire King; Jonathan Sebat Journal: Nat Genet Date: 2009-10-25 Impact factor: 38.330
Authors: Isaac R Galatzer-Levy; Karen-Inge Karstoft; Alexander Statnikov; Arieh Y Shalev Journal: J Psychiatr Res Date: 2014-09-16 Impact factor: 4.791
Authors: S R Clark; B T Baune; K O Schubert; S Lavoie; S Smesny; S M Rice; M R Schäfer; F Benninger; M Feucht; C M Klier; P D McGorry; G P Amminger Journal: Transl Psychiatry Date: 2016-09-20 Impact factor: 6.222
Authors: Sanne H Booij; Marieke Wichers; Peter de Jonge; Sjoerd Sytema; Jim van Os; Lex Wunderink; Johanna T W Wigman Journal: BMJ Open Date: 2018-01-21 Impact factor: 2.692
Authors: C A Bousman; A R Yung; C Pantelis; J A Ellis; R A Chavez; B Nelson; A Lin; S J Wood; G P Amminger; D Velakoulis; P D McGorry; I P Everall; D L Foley Journal: Transl Psychiatry Date: 2013-04-30 Impact factor: 6.222