Migraine classification using magnetic resonance imaging resting-state functional connectivity data

Catherine D. Chong, Nathan Gaw, Yinlin Fu, Jing Li, Teresa Wu, Todd J Schwedt

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Background This study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls. Methods This study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain classification algorithm that tested the accuracy of determining whether an individual brain MRI belongs to someone with migraine or to a healthy control. Results The best classification accuracy using a 10-fold cross-validation method was 86.1%. Resting functional connectivity of the right middle temporal, posterior insula, middle cingulate, left ventromedial prefrontal and bilateral amygdala regions best discriminated the migraine brain from that of a healthy control. Migraineurs with longer disease durations were classified more accurately (>14 years; 96.7% accuracy) compared to migraineurs with shorter disease durations (≤14 years; 82.1% accuracy). Conclusions Classification of migraine using rs-fMRI provides insights into pain circuits that are altered in migraine and could potentially contribute to the development of a new, noninvasive migraine biomarker. Migraineurs with longer disease burden were classified more accurately than migraineurs with shorter disease burden, potentially indicating that disease duration leads to reorganization of brain circuitry.

Original languageEnglish (US)
Pages (from-to)828-844
Number of pages17
JournalCephalalgia
Volume37
Issue number9
DOIs
StatePublished - Aug 1 2017

Fingerprint

Migraine Disorders
Magnetic Resonance Imaging
Brain
Neuroimaging
Magnetic Resonance Spectroscopy
Biomarkers
Pain
Amygdala

Keywords

  • classification
  • magnetic resonance imaging
  • Migraine
  • neuroimaging
  • principal component analysis
  • resting-state functional connectivity

ASJC Scopus subject areas

  • Clinical Neurology

Cite this

Migraine classification using magnetic resonance imaging resting-state functional connectivity data. / Chong, Catherine D.; Gaw, Nathan; Fu, Yinlin; Li, Jing; Wu, Teresa; Schwedt, Todd J.

In: Cephalalgia, Vol. 37, No. 9, 01.08.2017, p. 828-844.

Research output: Contribution to journalArticle

Chong, Catherine D. ; Gaw, Nathan ; Fu, Yinlin ; Li, Jing ; Wu, Teresa ; Schwedt, Todd J. / Migraine classification using magnetic resonance imaging resting-state functional connectivity data. In: Cephalalgia. 2017 ; Vol. 37, No. 9. pp. 828-844.
@article{d6db25f95b6c40ee94b6c842483f416e,
title = "Migraine classification using magnetic resonance imaging resting-state functional connectivity data",
abstract = "Background This study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls. Methods This study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain classification algorithm that tested the accuracy of determining whether an individual brain MRI belongs to someone with migraine or to a healthy control. Results The best classification accuracy using a 10-fold cross-validation method was 86.1{\%}. Resting functional connectivity of the right middle temporal, posterior insula, middle cingulate, left ventromedial prefrontal and bilateral amygdala regions best discriminated the migraine brain from that of a healthy control. Migraineurs with longer disease durations were classified more accurately (>14 years; 96.7{\%} accuracy) compared to migraineurs with shorter disease durations (≤14 years; 82.1{\%} accuracy). Conclusions Classification of migraine using rs-fMRI provides insights into pain circuits that are altered in migraine and could potentially contribute to the development of a new, noninvasive migraine biomarker. Migraineurs with longer disease burden were classified more accurately than migraineurs with shorter disease burden, potentially indicating that disease duration leads to reorganization of brain circuitry.",
keywords = "classification, magnetic resonance imaging, Migraine, neuroimaging, principal component analysis, resting-state functional connectivity",
author = "Chong, {Catherine D.} and Nathan Gaw and Yinlin Fu and Jing Li and Teresa Wu and Schwedt, {Todd J}",
year = "2017",
month = "8",
day = "1",
doi = "10.1177/0333102416652091",
language = "English (US)",
volume = "37",
pages = "828--844",
journal = "Cephalalgia",
issn = "0333-1024",
publisher = "SAGE Publications Ltd",
number = "9",

}

TY - JOUR

T1 - Migraine classification using magnetic resonance imaging resting-state functional connectivity data

AU - Chong, Catherine D.

AU - Gaw, Nathan

AU - Fu, Yinlin

AU - Li, Jing

AU - Wu, Teresa

AU - Schwedt, Todd J

PY - 2017/8/1

Y1 - 2017/8/1

N2 - Background This study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls. Methods This study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain classification algorithm that tested the accuracy of determining whether an individual brain MRI belongs to someone with migraine or to a healthy control. Results The best classification accuracy using a 10-fold cross-validation method was 86.1%. Resting functional connectivity of the right middle temporal, posterior insula, middle cingulate, left ventromedial prefrontal and bilateral amygdala regions best discriminated the migraine brain from that of a healthy control. Migraineurs with longer disease durations were classified more accurately (>14 years; 96.7% accuracy) compared to migraineurs with shorter disease durations (≤14 years; 82.1% accuracy). Conclusions Classification of migraine using rs-fMRI provides insights into pain circuits that are altered in migraine and could potentially contribute to the development of a new, noninvasive migraine biomarker. Migraineurs with longer disease burden were classified more accurately than migraineurs with shorter disease burden, potentially indicating that disease duration leads to reorganization of brain circuitry.

AB - Background This study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls. Methods This study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain classification algorithm that tested the accuracy of determining whether an individual brain MRI belongs to someone with migraine or to a healthy control. Results The best classification accuracy using a 10-fold cross-validation method was 86.1%. Resting functional connectivity of the right middle temporal, posterior insula, middle cingulate, left ventromedial prefrontal and bilateral amygdala regions best discriminated the migraine brain from that of a healthy control. Migraineurs with longer disease durations were classified more accurately (>14 years; 96.7% accuracy) compared to migraineurs with shorter disease durations (≤14 years; 82.1% accuracy). Conclusions Classification of migraine using rs-fMRI provides insights into pain circuits that are altered in migraine and could potentially contribute to the development of a new, noninvasive migraine biomarker. Migraineurs with longer disease burden were classified more accurately than migraineurs with shorter disease burden, potentially indicating that disease duration leads to reorganization of brain circuitry.

KW - classification

KW - magnetic resonance imaging

KW - Migraine

KW - neuroimaging

KW - principal component analysis

KW - resting-state functional connectivity

UR - http://www.scopus.com/inward/record.url?scp=85027449687&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85027449687&partnerID=8YFLogxK

U2 - 10.1177/0333102416652091

DO - 10.1177/0333102416652091

M3 - Article

C2 - 27306407

AN - SCOPUS:85027449687

VL - 37

SP - 828

EP - 844

JO - Cephalalgia

JF - Cephalalgia

SN - 0333-1024

IS - 9

ER -