Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task

Laerke Gebser Krohne, Yi Wang, Jesper Løve Hinrich, Morten Mørup, Raymond C K Chan, Kristoffer Hougaard Madsen*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

Abstract

Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.
Original languageEnglish
JournalHuman Brain Mapping
Volume40
Issue number17
Pages (from-to)4965-4981
Number of pages17
ISSN1065-9471
DOIs
Publication statusPublished - 2019

Keywords

  • Archetypical analysis
  • Decomposition
  • Functional connectivity
  • Social anhedonia
  • Support vector classification

Cite this

@article{64e5e32000e54217ba9e000c60561fd9,
title = "Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task",
abstract = "Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.",
keywords = "Archetypical analysis, Decomposition, Functional connectivity, Social anhedonia, Support vector classification",
author = "Krohne, {Laerke Gebser} and Yi Wang and Hinrich, {Jesper L{\o}ve} and Morten M{\o}rup and Chan, {Raymond C K} and Madsen, {Kristoffer Hougaard}",
year = "2019",
doi = "10.1002/hbm.24751",
language = "English",
volume = "40",
pages = "4965--4981",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "JohnWiley & Sons, Inc.",
number = "17",

}

Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task. / Krohne, Laerke Gebser; Wang, Yi; Hinrich, Jesper Løve; Mørup, Morten; Chan, Raymond C K; Madsen, Kristoffer Hougaard.

In: Human Brain Mapping, Vol. 40, No. 17, 2019, p. 4965-4981.

Research output: Contribution to journalJournal articleResearchpeer-review

TY - JOUR

T1 - Classification of social anhedonia using temporal and spatial network features from a social cognition fMRI task

AU - Krohne, Laerke Gebser

AU - Wang, Yi

AU - Hinrich, Jesper Løve

AU - Mørup, Morten

AU - Chan, Raymond C K

AU - Madsen, Kristoffer Hougaard

PY - 2019

Y1 - 2019

N2 - Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.

AB - Previous studies have suggested that the degree of social anhedonia reflects the vulnerability for developing schizophrenia. However, only few studies have investigated how functional network changes are related to social anhedonia. The aim of this fMRI study was to classify subjects according to their degree of social anhedonia using supervised machine learning. More specifically, we extracted both spatial and temporal network features during a social cognition task from 70 subjects, and used support vector machines for classification. Since impairment in social cognition is well established in schizophrenia-spectrum disorders, the subjects performed a comic strip task designed to specifically probe theory of mind (ToM) and empathy processing. Features representing both temporal (time series) and network dynamics were extracted using task activation maps, seed region analysis, independent component analysis (ICA), and a newly developed multi-subject archetypal analysis (MSAA), which here aimed to further bridge aspects of both seed region analysis and decomposition by incorporating a spotlight approach.We found significant classification of subjects with elevated levels of social anhedonia when using the times series extracted using MSAA, indicating that temporal dynamics carry important information for classification of social anhedonia. Interestingly, we found that the same time series yielded the highest classification performance in a task classification of the ToM condition. Finally, the spatial network corresponding to that time series included both prefrontal and temporal-parietal regions as well as insula activity, which previously have been related schizotypy and the development of schizophrenia.

KW - Archetypical analysis

KW - Decomposition

KW - Functional connectivity

KW - Social anhedonia

KW - Support vector classification

U2 - 10.1002/hbm.24751

DO - 10.1002/hbm.24751

M3 - Journal article

VL - 40

SP - 4965

EP - 4981

JO - Human Brain Mapping

JF - Human Brain Mapping

SN - 1065-9471

IS - 17

ER -