Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition

Nikolaos Koutsouleris, Eva M. Meisenzahl, Christos Davatzikos, Ronald Bottlender, Thomas Frodl, Johanna Scheuerecker, Gisela Schmitt, Thomas Zetzsche, Petra Decker, Maximilian Reiser, Hans Jürgen Möller, Christian Gaser

Research output: Contribution to journalArticle

Abstract

Context: Identification of individuals at high risk of developing psychosis has relied on prodromal symptomatology. Recently, machine learning algorithms have been successfully used for magnetic resonance imaging-based diagnostic classification of neuropsychiatric patient populations. Objective: To determine whether multivariate neuroanatomical pattern classification facilitates identification of individuals in different at-risk mental states (ARMS) of psychosis and enables the prediction of disease transition at the individual level. Design: Multivariate neuroanatomical pattern classification was performed on the structural magnetic resonance imaging data of individuals in early or late ARMS vs healthy controls (HCs). The predictive power of the method was then evaluated by categorizing the baseline imaging data of individuals with transition to psychosis vs those without transition vs HCs after 4 years of clinical follow-up. Classification generalizability was estimated by cross-validation and by categorizing an independent cohort of 45 new HCs. Setting: Departments of Psychiatry and Psychotherapy, Ludwig-Maximilians- University, Munich, Germany. Participants: The first classification analysis included 20 early and 25 late at-risk individuals and 25 matched HCs. The second analysis consisted of 15 individuals with transition, 18 without transition, and 17 matched HCs. Main Outcome Measures: Specificity, sensitivity, and accuracy of classification. Results: The 3-group, cross-validated classification accuracies of the first analysis were 86% (HCs vs the rest), 91% (early at-risk individuals vs the rest), and 86% (late at-risk individuals vs the rest). The accuracies in the second analysis were 90% (HCs vs the rest), 88% (individuals with transition vs the rest), and 86% (individuals without transition vs the rest). Independent HCs were correctly classified in 96% (first analysis) and 93% (second analysis) of cases. Conclusions: Different ARMSs and their clinical outcomes may be reliably identified on an individual basis by assessing patterns of whole-brain neuroanatomical abnormalities. These patterns may serve as valuable biomarkers for the clinician to guide early detection in the prodromal phase of psychosis.

Original languageEnglish (US)
Pages (from-to)700-712
Number of pages13
JournalArchives of General Psychiatry
Volume66
Issue number7
DOIs
StatePublished - Jul 2009
Externally publishedYes

Fingerprint

Psychotic Disorders
Magnetic Resonance Imaging
Psychotherapy
Germany
Psychiatry
Biomarkers
Outcome Assessment (Health Care)
Sensitivity and Specificity
Brain
Population

ASJC Scopus subject areas

  • Psychiatry and Mental health

Cite this

Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition. / Koutsouleris, Nikolaos; Meisenzahl, Eva M.; Davatzikos, Christos; Bottlender, Ronald; Frodl, Thomas; Scheuerecker, Johanna; Schmitt, Gisela; Zetzsche, Thomas; Decker, Petra; Reiser, Maximilian; Möller, Hans Jürgen; Gaser, Christian.

In: Archives of General Psychiatry, Vol. 66, No. 7, 07.2009, p. 700-712.

Research output: Contribution to journalArticle

Koutsouleris, N, Meisenzahl, EM, Davatzikos, C, Bottlender, R, Frodl, T, Scheuerecker, J, Schmitt, G, Zetzsche, T, Decker, P, Reiser, M, Möller, HJ & Gaser, C 2009, 'Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition', Archives of General Psychiatry, vol. 66, no. 7, pp. 700-712. https://doi.org/10.1001/archgenpsychiatry.2009.62
Koutsouleris, Nikolaos ; Meisenzahl, Eva M. ; Davatzikos, Christos ; Bottlender, Ronald ; Frodl, Thomas ; Scheuerecker, Johanna ; Schmitt, Gisela ; Zetzsche, Thomas ; Decker, Petra ; Reiser, Maximilian ; Möller, Hans Jürgen ; Gaser, Christian. / Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition. In: Archives of General Psychiatry. 2009 ; Vol. 66, No. 7. pp. 700-712.
@article{95a56c365bc94bb3b6765d7ae7a1fbff,
title = "Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition",
abstract = "Context: Identification of individuals at high risk of developing psychosis has relied on prodromal symptomatology. Recently, machine learning algorithms have been successfully used for magnetic resonance imaging-based diagnostic classification of neuropsychiatric patient populations. Objective: To determine whether multivariate neuroanatomical pattern classification facilitates identification of individuals in different at-risk mental states (ARMS) of psychosis and enables the prediction of disease transition at the individual level. Design: Multivariate neuroanatomical pattern classification was performed on the structural magnetic resonance imaging data of individuals in early or late ARMS vs healthy controls (HCs). The predictive power of the method was then evaluated by categorizing the baseline imaging data of individuals with transition to psychosis vs those without transition vs HCs after 4 years of clinical follow-up. Classification generalizability was estimated by cross-validation and by categorizing an independent cohort of 45 new HCs. Setting: Departments of Psychiatry and Psychotherapy, Ludwig-Maximilians- University, Munich, Germany. Participants: The first classification analysis included 20 early and 25 late at-risk individuals and 25 matched HCs. The second analysis consisted of 15 individuals with transition, 18 without transition, and 17 matched HCs. Main Outcome Measures: Specificity, sensitivity, and accuracy of classification. Results: The 3-group, cross-validated classification accuracies of the first analysis were 86{\%} (HCs vs the rest), 91{\%} (early at-risk individuals vs the rest), and 86{\%} (late at-risk individuals vs the rest). The accuracies in the second analysis were 90{\%} (HCs vs the rest), 88{\%} (individuals with transition vs the rest), and 86{\%} (individuals without transition vs the rest). Independent HCs were correctly classified in 96{\%} (first analysis) and 93{\%} (second analysis) of cases. Conclusions: Different ARMSs and their clinical outcomes may be reliably identified on an individual basis by assessing patterns of whole-brain neuroanatomical abnormalities. These patterns may serve as valuable biomarkers for the clinician to guide early detection in the prodromal phase of psychosis.",
author = "Nikolaos Koutsouleris and Meisenzahl, {Eva M.} and Christos Davatzikos and Ronald Bottlender and Thomas Frodl and Johanna Scheuerecker and Gisela Schmitt and Thomas Zetzsche and Petra Decker and Maximilian Reiser and M{\"o}ller, {Hans J{\"u}rgen} and Christian Gaser",
year = "2009",
month = "7",
doi = "10.1001/archgenpsychiatry.2009.62",
language = "English (US)",
volume = "66",
pages = "700--712",
journal = "JAMA Psychiatry",
issn = "2168-622X",
publisher = "American Medical Association",
number = "7",

}

TY - JOUR

T1 - Use of neuroanatomical pattern classification to identify subjects in at-risk mental states of psychosis and predict disease transition

AU - Koutsouleris, Nikolaos

AU - Meisenzahl, Eva M.

AU - Davatzikos, Christos

AU - Bottlender, Ronald

AU - Frodl, Thomas

AU - Scheuerecker, Johanna

AU - Schmitt, Gisela

AU - Zetzsche, Thomas

AU - Decker, Petra

AU - Reiser, Maximilian

AU - Möller, Hans Jürgen

AU - Gaser, Christian

PY - 2009/7

Y1 - 2009/7

N2 - Context: Identification of individuals at high risk of developing psychosis has relied on prodromal symptomatology. Recently, machine learning algorithms have been successfully used for magnetic resonance imaging-based diagnostic classification of neuropsychiatric patient populations. Objective: To determine whether multivariate neuroanatomical pattern classification facilitates identification of individuals in different at-risk mental states (ARMS) of psychosis and enables the prediction of disease transition at the individual level. Design: Multivariate neuroanatomical pattern classification was performed on the structural magnetic resonance imaging data of individuals in early or late ARMS vs healthy controls (HCs). The predictive power of the method was then evaluated by categorizing the baseline imaging data of individuals with transition to psychosis vs those without transition vs HCs after 4 years of clinical follow-up. Classification generalizability was estimated by cross-validation and by categorizing an independent cohort of 45 new HCs. Setting: Departments of Psychiatry and Psychotherapy, Ludwig-Maximilians- University, Munich, Germany. Participants: The first classification analysis included 20 early and 25 late at-risk individuals and 25 matched HCs. The second analysis consisted of 15 individuals with transition, 18 without transition, and 17 matched HCs. Main Outcome Measures: Specificity, sensitivity, and accuracy of classification. Results: The 3-group, cross-validated classification accuracies of the first analysis were 86% (HCs vs the rest), 91% (early at-risk individuals vs the rest), and 86% (late at-risk individuals vs the rest). The accuracies in the second analysis were 90% (HCs vs the rest), 88% (individuals with transition vs the rest), and 86% (individuals without transition vs the rest). Independent HCs were correctly classified in 96% (first analysis) and 93% (second analysis) of cases. Conclusions: Different ARMSs and their clinical outcomes may be reliably identified on an individual basis by assessing patterns of whole-brain neuroanatomical abnormalities. These patterns may serve as valuable biomarkers for the clinician to guide early detection in the prodromal phase of psychosis.

AB - Context: Identification of individuals at high risk of developing psychosis has relied on prodromal symptomatology. Recently, machine learning algorithms have been successfully used for magnetic resonance imaging-based diagnostic classification of neuropsychiatric patient populations. Objective: To determine whether multivariate neuroanatomical pattern classification facilitates identification of individuals in different at-risk mental states (ARMS) of psychosis and enables the prediction of disease transition at the individual level. Design: Multivariate neuroanatomical pattern classification was performed on the structural magnetic resonance imaging data of individuals in early or late ARMS vs healthy controls (HCs). The predictive power of the method was then evaluated by categorizing the baseline imaging data of individuals with transition to psychosis vs those without transition vs HCs after 4 years of clinical follow-up. Classification generalizability was estimated by cross-validation and by categorizing an independent cohort of 45 new HCs. Setting: Departments of Psychiatry and Psychotherapy, Ludwig-Maximilians- University, Munich, Germany. Participants: The first classification analysis included 20 early and 25 late at-risk individuals and 25 matched HCs. The second analysis consisted of 15 individuals with transition, 18 without transition, and 17 matched HCs. Main Outcome Measures: Specificity, sensitivity, and accuracy of classification. Results: The 3-group, cross-validated classification accuracies of the first analysis were 86% (HCs vs the rest), 91% (early at-risk individuals vs the rest), and 86% (late at-risk individuals vs the rest). The accuracies in the second analysis were 90% (HCs vs the rest), 88% (individuals with transition vs the rest), and 86% (individuals without transition vs the rest). Independent HCs were correctly classified in 96% (first analysis) and 93% (second analysis) of cases. Conclusions: Different ARMSs and their clinical outcomes may be reliably identified on an individual basis by assessing patterns of whole-brain neuroanatomical abnormalities. These patterns may serve as valuable biomarkers for the clinician to guide early detection in the prodromal phase of psychosis.

UR - http://www.scopus.com/inward/record.url?scp=67650457029&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650457029&partnerID=8YFLogxK

U2 - 10.1001/archgenpsychiatry.2009.62

DO - 10.1001/archgenpsychiatry.2009.62

M3 - Article

C2 - 19581561

AN - SCOPUS:67650457029

VL - 66

SP - 700

EP - 712

JO - JAMA Psychiatry

JF - JAMA Psychiatry

SN - 2168-622X

IS - 7

ER -