Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods

Nicolas Honnorat, Aoyan Dong, Eva Meisenzahl-Lechner, Nikolaos Koutsouleris, Christos Davatzikos

Research output: Contribution to journalArticle

Abstract

Schizophrenia is associated with heterogeneous clinical symptoms and neuroanatomical alterations. In this work, we aim to disentangle the patterns of neuroanatomical alterations underlying a heterogeneous population of patients using a semi-supervised clustering method. We apply this strategy to a cohort of patients with schizophrenia of varying extends of disease duration, and we describe the neuroanatomical, demographic and clinical characteristics of the subtypes discovered. Methods: We analyze the neuroanatomical heterogeneity of 157 patients diagnosed with Schizophrenia, relative to a control population of 169 subjects, using a machine learning method called CHIMERA. CHIMERA clusters the differences between patients and a demographically-matched population of healthy subjects, rather than clustering patients themselves, thereby specifically assessing disease-related neuroanatomical alterations. Voxel-Based Morphometry was conducted to visualize the neuroanatomical patterns associated with each group. The clinical presentation and the demographics of the groups were then investigated. Results: Three subgroups were identified. The first two differed substantially, in that one involved predominantly temporal-thalamic-peri-Sylvian regions, whereas the other involved predominantly frontal regions and the thalamus. Both subtypes included primarily male patients. The third pattern was a mix of these two and presented milder neuroanatomic alterations and comprised a comparable number of men and women. VBM and statistical analyses suggest that these groups could correspond to different neuroanatomical dimensions of schizophrenia. Conclusion: Our analysis suggests that schizophrenia presents distinct neuroanatomical variants. This variability points to the need for a dimensional neuroanatomical approach using data-driven, mathematically principled multivariate pattern analysis methods, and should be taken into account in clinical studies.

Original languageEnglish (US)
JournalSchizophrenia Research
DOIs
StateAccepted/In press - Jan 1 2017

Fingerprint

Schizophrenia
Cluster Analysis
Demography
Population
Thalamus
Supervised Machine Learning
Healthy Volunteers
Multivariate Analysis

Keywords

  • Gray matter
  • Machine learning
  • Multivariate pattern analysis
  • Schizophrenia
  • VBM
  • White matter

ASJC Scopus subject areas

  • Psychiatry and Mental health
  • Biological Psychiatry

Cite this

Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods. / Honnorat, Nicolas; Dong, Aoyan; Meisenzahl-Lechner, Eva; Koutsouleris, Nikolaos; Davatzikos, Christos.

In: Schizophrenia Research, 01.01.2017.

Research output: Contribution to journalArticle

Honnorat, Nicolas ; Dong, Aoyan ; Meisenzahl-Lechner, Eva ; Koutsouleris, Nikolaos ; Davatzikos, Christos. / Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods. In: Schizophrenia Research. 2017.
@article{142eaab481e44c91b387e31b50925eae,
title = "Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods",
abstract = "Schizophrenia is associated with heterogeneous clinical symptoms and neuroanatomical alterations. In this work, we aim to disentangle the patterns of neuroanatomical alterations underlying a heterogeneous population of patients using a semi-supervised clustering method. We apply this strategy to a cohort of patients with schizophrenia of varying extends of disease duration, and we describe the neuroanatomical, demographic and clinical characteristics of the subtypes discovered. Methods: We analyze the neuroanatomical heterogeneity of 157 patients diagnosed with Schizophrenia, relative to a control population of 169 subjects, using a machine learning method called CHIMERA. CHIMERA clusters the differences between patients and a demographically-matched population of healthy subjects, rather than clustering patients themselves, thereby specifically assessing disease-related neuroanatomical alterations. Voxel-Based Morphometry was conducted to visualize the neuroanatomical patterns associated with each group. The clinical presentation and the demographics of the groups were then investigated. Results: Three subgroups were identified. The first two differed substantially, in that one involved predominantly temporal-thalamic-peri-Sylvian regions, whereas the other involved predominantly frontal regions and the thalamus. Both subtypes included primarily male patients. The third pattern was a mix of these two and presented milder neuroanatomic alterations and comprised a comparable number of men and women. VBM and statistical analyses suggest that these groups could correspond to different neuroanatomical dimensions of schizophrenia. Conclusion: Our analysis suggests that schizophrenia presents distinct neuroanatomical variants. This variability points to the need for a dimensional neuroanatomical approach using data-driven, mathematically principled multivariate pattern analysis methods, and should be taken into account in clinical studies.",
keywords = "Gray matter, Machine learning, Multivariate pattern analysis, Schizophrenia, VBM, White matter",
author = "Nicolas Honnorat and Aoyan Dong and Eva Meisenzahl-Lechner and Nikolaos Koutsouleris and Christos Davatzikos",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.schres.2017.12.008",
language = "English (US)",
journal = "Schizophrenia Research",
issn = "0920-9964",
publisher = "Elsevier",

}

TY - JOUR

T1 - Neuroanatomical heterogeneity of schizophrenia revealed by semi-supervised machine learning methods

AU - Honnorat, Nicolas

AU - Dong, Aoyan

AU - Meisenzahl-Lechner, Eva

AU - Koutsouleris, Nikolaos

AU - Davatzikos, Christos

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Schizophrenia is associated with heterogeneous clinical symptoms and neuroanatomical alterations. In this work, we aim to disentangle the patterns of neuroanatomical alterations underlying a heterogeneous population of patients using a semi-supervised clustering method. We apply this strategy to a cohort of patients with schizophrenia of varying extends of disease duration, and we describe the neuroanatomical, demographic and clinical characteristics of the subtypes discovered. Methods: We analyze the neuroanatomical heterogeneity of 157 patients diagnosed with Schizophrenia, relative to a control population of 169 subjects, using a machine learning method called CHIMERA. CHIMERA clusters the differences between patients and a demographically-matched population of healthy subjects, rather than clustering patients themselves, thereby specifically assessing disease-related neuroanatomical alterations. Voxel-Based Morphometry was conducted to visualize the neuroanatomical patterns associated with each group. The clinical presentation and the demographics of the groups were then investigated. Results: Three subgroups were identified. The first two differed substantially, in that one involved predominantly temporal-thalamic-peri-Sylvian regions, whereas the other involved predominantly frontal regions and the thalamus. Both subtypes included primarily male patients. The third pattern was a mix of these two and presented milder neuroanatomic alterations and comprised a comparable number of men and women. VBM and statistical analyses suggest that these groups could correspond to different neuroanatomical dimensions of schizophrenia. Conclusion: Our analysis suggests that schizophrenia presents distinct neuroanatomical variants. This variability points to the need for a dimensional neuroanatomical approach using data-driven, mathematically principled multivariate pattern analysis methods, and should be taken into account in clinical studies.

AB - Schizophrenia is associated with heterogeneous clinical symptoms and neuroanatomical alterations. In this work, we aim to disentangle the patterns of neuroanatomical alterations underlying a heterogeneous population of patients using a semi-supervised clustering method. We apply this strategy to a cohort of patients with schizophrenia of varying extends of disease duration, and we describe the neuroanatomical, demographic and clinical characteristics of the subtypes discovered. Methods: We analyze the neuroanatomical heterogeneity of 157 patients diagnosed with Schizophrenia, relative to a control population of 169 subjects, using a machine learning method called CHIMERA. CHIMERA clusters the differences between patients and a demographically-matched population of healthy subjects, rather than clustering patients themselves, thereby specifically assessing disease-related neuroanatomical alterations. Voxel-Based Morphometry was conducted to visualize the neuroanatomical patterns associated with each group. The clinical presentation and the demographics of the groups were then investigated. Results: Three subgroups were identified. The first two differed substantially, in that one involved predominantly temporal-thalamic-peri-Sylvian regions, whereas the other involved predominantly frontal regions and the thalamus. Both subtypes included primarily male patients. The third pattern was a mix of these two and presented milder neuroanatomic alterations and comprised a comparable number of men and women. VBM and statistical analyses suggest that these groups could correspond to different neuroanatomical dimensions of schizophrenia. Conclusion: Our analysis suggests that schizophrenia presents distinct neuroanatomical variants. This variability points to the need for a dimensional neuroanatomical approach using data-driven, mathematically principled multivariate pattern analysis methods, and should be taken into account in clinical studies.

KW - Gray matter

KW - Machine learning

KW - Multivariate pattern analysis

KW - Schizophrenia

KW - VBM

KW - White matter

UR - http://www.scopus.com/inward/record.url?scp=85038844131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85038844131&partnerID=8YFLogxK

U2 - 10.1016/j.schres.2017.12.008

DO - 10.1016/j.schres.2017.12.008

M3 - Article

JO - Schizophrenia Research

JF - Schizophrenia Research

SN - 0920-9964

ER -