Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia

Jong H. Yoon, Danh V. Nguyen, Lindsey M. McVay, Paul Deramo, Michael J. Minzenberg, John D Ragland, Tara Niendham, Marjorie Solomon Friedman, Cameron S Carter

Research output: Contribution to journalArticle

20 Citations (Scopus)

Abstract

The establishment of a neurobiologically based nosological system is one of the ultimate goals of modern biological psychiatry research. Developments in neuroimaging and statistical/machine learning have provided useful basic tools for these efforts. Recent studies have demonstrated the utility of fMRI as input data for the classification of schizophrenia, but none, to date, has used fMRI of cognitive control for this purpose. In this study, we evaluated the accuracy of an unbiased classification method on fMRI data from a large cohort of subjects with first episode schizophrenia and a cohort of age matched healthy control subjects while they completed the AX version of the Continuous Performance Task (AX-CPT). We compared these results to classifications based on AX-CPT behavioral data. Classification accuracy for DSM-IV defined schizophrenia using fMRI data was modest and comparable to classifications conducted with behavioral data. Interestingly fMRI classifications did however identify a distinct subgroup of patients with greater behavioral disorganization, whereas behavioral data classifications did not. These results suggest that fMRI-based classification could be a useful tool in defining a neurobiologically distinct subgroup within the clinically defined syndrome of schizophrenia, reflecting alterations in discrete neural circuits. Independent validation of classification-based phenotypes using other biological data such as genetics would provide a strong test of this hypothesis.

Original languageEnglish (US)
Pages (from-to)28-33
Number of pages6
JournalSchizophrenia Research
Volume135
Issue number1-3
DOIs
StatePublished - Mar 2012

Fingerprint

Schizophrenia
Magnetic Resonance Imaging
Task Performance and Analysis
Biological Psychiatry
Neuroimaging
Diagnostic and Statistical Manual of Mental Disorders
Healthy Volunteers
Phenotype
Research

Keywords

  • Automated classification
  • FMRI
  • Nosology
  • Schizophrenia

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia. / Yoon, Jong H.; Nguyen, Danh V.; McVay, Lindsey M.; Deramo, Paul; Minzenberg, Michael J.; Ragland, John D; Niendham, Tara; Friedman, Marjorie Solomon; Carter, Cameron S.

In: Schizophrenia Research, Vol. 135, No. 1-3, 03.2012, p. 28-33.

Research output: Contribution to journalArticle

Yoon, Jong H. ; Nguyen, Danh V. ; McVay, Lindsey M. ; Deramo, Paul ; Minzenberg, Michael J. ; Ragland, John D ; Niendham, Tara ; Friedman, Marjorie Solomon ; Carter, Cameron S. / Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia. In: Schizophrenia Research. 2012 ; Vol. 135, No. 1-3. pp. 28-33.
@article{e9fd9d870dfd408bab96c0d7264750a0,
title = "Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia",
abstract = "The establishment of a neurobiologically based nosological system is one of the ultimate goals of modern biological psychiatry research. Developments in neuroimaging and statistical/machine learning have provided useful basic tools for these efforts. Recent studies have demonstrated the utility of fMRI as input data for the classification of schizophrenia, but none, to date, has used fMRI of cognitive control for this purpose. In this study, we evaluated the accuracy of an unbiased classification method on fMRI data from a large cohort of subjects with first episode schizophrenia and a cohort of age matched healthy control subjects while they completed the AX version of the Continuous Performance Task (AX-CPT). We compared these results to classifications based on AX-CPT behavioral data. Classification accuracy for DSM-IV defined schizophrenia using fMRI data was modest and comparable to classifications conducted with behavioral data. Interestingly fMRI classifications did however identify a distinct subgroup of patients with greater behavioral disorganization, whereas behavioral data classifications did not. These results suggest that fMRI-based classification could be a useful tool in defining a neurobiologically distinct subgroup within the clinically defined syndrome of schizophrenia, reflecting alterations in discrete neural circuits. Independent validation of classification-based phenotypes using other biological data such as genetics would provide a strong test of this hypothesis.",
keywords = "Automated classification, FMRI, Nosology, Schizophrenia",
author = "Yoon, {Jong H.} and Nguyen, {Danh V.} and McVay, {Lindsey M.} and Paul Deramo and Minzenberg, {Michael J.} and Ragland, {John D} and Tara Niendham and Friedman, {Marjorie Solomon} and Carter, {Cameron S}",
year = "2012",
month = "3",
doi = "10.1016/j.schres.2012.01.001",
language = "English (US)",
volume = "135",
pages = "28--33",
journal = "Schizophrenia Research",
issn = "0920-9964",
publisher = "Elsevier",
number = "1-3",

}

TY - JOUR

T1 - Automated classification of fMRI during cognitive control identifies more severely disorganized subjects with schizophrenia

AU - Yoon, Jong H.

AU - Nguyen, Danh V.

AU - McVay, Lindsey M.

AU - Deramo, Paul

AU - Minzenberg, Michael J.

AU - Ragland, John D

AU - Niendham, Tara

AU - Friedman, Marjorie Solomon

AU - Carter, Cameron S

PY - 2012/3

Y1 - 2012/3

N2 - The establishment of a neurobiologically based nosological system is one of the ultimate goals of modern biological psychiatry research. Developments in neuroimaging and statistical/machine learning have provided useful basic tools for these efforts. Recent studies have demonstrated the utility of fMRI as input data for the classification of schizophrenia, but none, to date, has used fMRI of cognitive control for this purpose. In this study, we evaluated the accuracy of an unbiased classification method on fMRI data from a large cohort of subjects with first episode schizophrenia and a cohort of age matched healthy control subjects while they completed the AX version of the Continuous Performance Task (AX-CPT). We compared these results to classifications based on AX-CPT behavioral data. Classification accuracy for DSM-IV defined schizophrenia using fMRI data was modest and comparable to classifications conducted with behavioral data. Interestingly fMRI classifications did however identify a distinct subgroup of patients with greater behavioral disorganization, whereas behavioral data classifications did not. These results suggest that fMRI-based classification could be a useful tool in defining a neurobiologically distinct subgroup within the clinically defined syndrome of schizophrenia, reflecting alterations in discrete neural circuits. Independent validation of classification-based phenotypes using other biological data such as genetics would provide a strong test of this hypothesis.

AB - The establishment of a neurobiologically based nosological system is one of the ultimate goals of modern biological psychiatry research. Developments in neuroimaging and statistical/machine learning have provided useful basic tools for these efforts. Recent studies have demonstrated the utility of fMRI as input data for the classification of schizophrenia, but none, to date, has used fMRI of cognitive control for this purpose. In this study, we evaluated the accuracy of an unbiased classification method on fMRI data from a large cohort of subjects with first episode schizophrenia and a cohort of age matched healthy control subjects while they completed the AX version of the Continuous Performance Task (AX-CPT). We compared these results to classifications based on AX-CPT behavioral data. Classification accuracy for DSM-IV defined schizophrenia using fMRI data was modest and comparable to classifications conducted with behavioral data. Interestingly fMRI classifications did however identify a distinct subgroup of patients with greater behavioral disorganization, whereas behavioral data classifications did not. These results suggest that fMRI-based classification could be a useful tool in defining a neurobiologically distinct subgroup within the clinically defined syndrome of schizophrenia, reflecting alterations in discrete neural circuits. Independent validation of classification-based phenotypes using other biological data such as genetics would provide a strong test of this hypothesis.

KW - Automated classification

KW - FMRI

KW - Nosology

KW - Schizophrenia

UR - http://www.scopus.com/inward/record.url?scp=84857234687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857234687&partnerID=8YFLogxK

U2 - 10.1016/j.schres.2012.01.001

DO - 10.1016/j.schres.2012.01.001

M3 - Article

C2 - 22277668

AN - SCOPUS:84857234687

VL - 135

SP - 28

EP - 33

JO - Schizophrenia Research

JF - Schizophrenia Research

SN - 0920-9964

IS - 1-3

ER -