Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level

William Petterson-Yeo; Stefania Benetti; Andre F. Marquand; F. Dell'Acqua; S.C.R Williams; Paul Allen; D. Prata; Philip McGuire; Andrea Mechelli

doi:10.1017/S003329171300024X

Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level

William Petterson-Yeo, Stefania Benetti, Andre F. Marquand, F. Dell'Acqua, S.C.R Williams, Paul Allen, D. Prata, Philip McGuire, Andrea Mechelli

Research output: Contribution to journal › Article

Abstract

Background. Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM.Method. Three age-and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested.Results. Successful classification accuracies (p<0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%).Conclusions. The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.

Original language	English
Pages (from-to)	2547-2562
Journal	Psychological Medicine
Volume	43
Issue number	12
DOIs	https://doi.org/10.1017/S003329171300024X
Publication status	Published - 2013

Access to Document

10.1017/S003329171300024X

http://dx.doi.org/10.1017/S003329171300024X

Cite this

@article{39a3f9eee71e47e293ae02ae9e18f5ab,

title = "Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level",

abstract = "Background. Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM.Method. Three age-and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested.Results. Successful classification accuracies (p<0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%).Conclusions. The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.",

author = "William Petterson-Yeo and Stefania Benetti and Marquand, {Andre F.} and F. Dell'Acqua and S.C.R Williams and Paul Allen and D. Prata and Philip McGuire and Andrea Mechelli",

year = "2013",

doi = "10.1017/S003329171300024X",

language = "English",

volume = "43",

pages = "2547--2562",

journal = "Psychological Medicine",

issn = "0033-2917",

publisher = "Cambridge University Press",

number = "12",

}

TY - JOUR

T1 - Using genetic, cognitive and multi-modal neuroimaging data to identify ultra-high-risk and first-episode psychosis at the individual level

AU - Petterson-Yeo, William

AU - Benetti, Stefania

AU - Marquand, Andre F.

AU - Dell'Acqua, F.

AU - Williams, S.C.R

AU - Allen, Paul

AU - Prata, D.

AU - McGuire, Philip

AU - Mechelli, Andrea

PY - 2013

Y1 - 2013

N2 - Background. Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM.Method. Three age-and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested.Results. Successful classification accuracies (p<0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%).Conclusions. The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.

AB - Background. Group-level results suggest that relative to healthy controls (HCs), ultra-high-risk (UHR) and first-episode psychosis (FEP) subjects show alterations in neuroanatomy, neurofunction and cognition that may be mediated genetically. It is unclear, however, whether these groups can be differentiated at single-subject level, for instance using the machine learning analysis support vector machine (SVM). Here, we used a multimodal approach to examine the ability of structural magnetic resonance imaging (sMRI), functional MRI (fMRI), diffusion tensor neuroimaging (DTI), genetic and cognitive data to differentiate between UHR, FEP and HC subjects at the single-subject level using SVM.Method. Three age-and gender-matched SVM paired comparison groups were created comprising 19, 19 and 15 subject pairs for FEP versus HC, UHR versus HC and FEP versus UHR, respectively. Genetic, sMRI, DTI, fMRI and cognitive data were obtained for each participant and the ability of each to discriminate subjects at the individual level in conjunction with SVM was tested.Results. Successful classification accuracies (p<0.05) comprised FEP versus HC (genotype, 67.86%; DTI, 65.79%; fMRI, 65.79% and 68.42%; cognitive data, 73.69%), UHR versus HC (sMRI, 68.42%; DTI, 65.79%), and FEP versus UHR (sMRI, 76.67%; fMRI, 73.33%; cognitive data, 66.67%).Conclusions. The results suggest that FEP subjects are identifiable at the individual level using a range of biological and cognitive measures. Comparatively, only sMRI and DTI allowed discrimination of UHR from HC subjects. For the first time FEP and UHR subjects have been shown to be directly differentiable at the single-subject level using cognitive, sMRI and fMRI data. Preliminarily, the results support clinical development of SVM to help inform identification of FEP and UHR subjects, though future work is needed to provide enhanced levels of accuracy.

U2 - 10.1017/S003329171300024X

DO - 10.1017/S003329171300024X

M3 - Article

SN - 0033-2917

VL - 43

SP - 2547

EP - 2562

JO - Psychological Medicine

JF - Psychological Medicine

IS - 12

ER -