Multivariate machine learning distinguishes cross-network dynamic functional connectivity patterns in state and trait neuropathic pain

Joshua C. Cheng, Anton Rogachov, Kasey S. Hemington, Aaron Kucyi, Rachael L. Bosma, Martin Lindquist, Robert D. Inman, Karen D. Davis

Research output: Contribution to journalArticle

Abstract

Communication within the brain is dynamic. Chronic pain can also be dynamic, with varying intensities experienced over time. Little is known of how brain dynamics are disrupted in chronic pain, or relates to patients' pain assessed at various timescales (eg, short-term state vs long-term trait). Patients experience pain "traits" indicative of their general condition, but also pain "states" that vary day to day. Here, we used network-based multivariate machine learning to determine how patterns in dynamic and static brain communication are related to different characteristics and timescales of chronic pain. Our models were based on resting-state dynamic functional connectivity (dFC) and static functional connectivity in patients with chronic neuropathic pain (NP) or non-NP. The most prominent networks in the models were the default mode, salience, and executive control networks. We also found that cross-network measures of dFC rather than static functional connectivity were better associated with patients' pain, but only in those with NP features. These associations were also more highly and widely associated with measures of trait rather than state pain. Furthermore, greater dynamic connectivity with executive control networks was associated with milder NP, but greater dynamic connectivity with limbic networks was associated with greater NP. Compared with healthy individuals, the dFC features most highly related to trait NP were also more abnormal in patients with greater pain. Our findings indicate that dFC reflects patients' overall pain condition (ie, trait pain), not just their current state, and is impacted by complexities in pain features beyond intensity.

Original languageEnglish (US)
Pages (from-to)1764-1776
Number of pages13
JournalPain
Volume159
Issue number9
DOIs
StatePublished - Sep 1 2018

Fingerprint

Neuralgia
Pain
Chronic Pain
Executive Function
Brain
Communication
Machine Learning

ASJC Scopus subject areas

  • Neurology
  • Clinical Neurology
  • Anesthesiology and Pain Medicine

Cite this

Multivariate machine learning distinguishes cross-network dynamic functional connectivity patterns in state and trait neuropathic pain. / Cheng, Joshua C.; Rogachov, Anton; Hemington, Kasey S.; Kucyi, Aaron; Bosma, Rachael L.; Lindquist, Martin; Inman, Robert D.; Davis, Karen D.

In: Pain, Vol. 159, No. 9, 01.09.2018, p. 1764-1776.

Research output: Contribution to journalArticle

Cheng, Joshua C. ; Rogachov, Anton ; Hemington, Kasey S. ; Kucyi, Aaron ; Bosma, Rachael L. ; Lindquist, Martin ; Inman, Robert D. ; Davis, Karen D. / Multivariate machine learning distinguishes cross-network dynamic functional connectivity patterns in state and trait neuropathic pain. In: Pain. 2018 ; Vol. 159, No. 9. pp. 1764-1776.
@article{c70bfbb796114713ad769ffd9e00ce1c,
title = "Multivariate machine learning distinguishes cross-network dynamic functional connectivity patterns in state and trait neuropathic pain",
abstract = "Communication within the brain is dynamic. Chronic pain can also be dynamic, with varying intensities experienced over time. Little is known of how brain dynamics are disrupted in chronic pain, or relates to patients' pain assessed at various timescales (eg, short-term state vs long-term trait). Patients experience pain {"}traits{"} indicative of their general condition, but also pain {"}states{"} that vary day to day. Here, we used network-based multivariate machine learning to determine how patterns in dynamic and static brain communication are related to different characteristics and timescales of chronic pain. Our models were based on resting-state dynamic functional connectivity (dFC) and static functional connectivity in patients with chronic neuropathic pain (NP) or non-NP. The most prominent networks in the models were the default mode, salience, and executive control networks. We also found that cross-network measures of dFC rather than static functional connectivity were better associated with patients' pain, but only in those with NP features. These associations were also more highly and widely associated with measures of trait rather than state pain. Furthermore, greater dynamic connectivity with executive control networks was associated with milder NP, but greater dynamic connectivity with limbic networks was associated with greater NP. Compared with healthy individuals, the dFC features most highly related to trait NP were also more abnormal in patients with greater pain. Our findings indicate that dFC reflects patients' overall pain condition (ie, trait pain), not just their current state, and is impacted by complexities in pain features beyond intensity.",
author = "Cheng, {Joshua C.} and Anton Rogachov and Hemington, {Kasey S.} and Aaron Kucyi and Bosma, {Rachael L.} and Martin Lindquist and Inman, {Robert D.} and Davis, {Karen D.}",
year = "2018",
month = "9",
day = "1",
doi = "10.1097/j.pain.0000000000001264",
language = "English (US)",
volume = "159",
pages = "1764--1776",
journal = "Pain",
issn = "0304-3959",
publisher = "Elsevier",
number = "9",

}

TY - JOUR

T1 - Multivariate machine learning distinguishes cross-network dynamic functional connectivity patterns in state and trait neuropathic pain

AU - Cheng, Joshua C.

AU - Rogachov, Anton

AU - Hemington, Kasey S.

AU - Kucyi, Aaron

AU - Bosma, Rachael L.

AU - Lindquist, Martin

AU - Inman, Robert D.

AU - Davis, Karen D.

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Communication within the brain is dynamic. Chronic pain can also be dynamic, with varying intensities experienced over time. Little is known of how brain dynamics are disrupted in chronic pain, or relates to patients' pain assessed at various timescales (eg, short-term state vs long-term trait). Patients experience pain "traits" indicative of their general condition, but also pain "states" that vary day to day. Here, we used network-based multivariate machine learning to determine how patterns in dynamic and static brain communication are related to different characteristics and timescales of chronic pain. Our models were based on resting-state dynamic functional connectivity (dFC) and static functional connectivity in patients with chronic neuropathic pain (NP) or non-NP. The most prominent networks in the models were the default mode, salience, and executive control networks. We also found that cross-network measures of dFC rather than static functional connectivity were better associated with patients' pain, but only in those with NP features. These associations were also more highly and widely associated with measures of trait rather than state pain. Furthermore, greater dynamic connectivity with executive control networks was associated with milder NP, but greater dynamic connectivity with limbic networks was associated with greater NP. Compared with healthy individuals, the dFC features most highly related to trait NP were also more abnormal in patients with greater pain. Our findings indicate that dFC reflects patients' overall pain condition (ie, trait pain), not just their current state, and is impacted by complexities in pain features beyond intensity.

AB - Communication within the brain is dynamic. Chronic pain can also be dynamic, with varying intensities experienced over time. Little is known of how brain dynamics are disrupted in chronic pain, or relates to patients' pain assessed at various timescales (eg, short-term state vs long-term trait). Patients experience pain "traits" indicative of their general condition, but also pain "states" that vary day to day. Here, we used network-based multivariate machine learning to determine how patterns in dynamic and static brain communication are related to different characteristics and timescales of chronic pain. Our models were based on resting-state dynamic functional connectivity (dFC) and static functional connectivity in patients with chronic neuropathic pain (NP) or non-NP. The most prominent networks in the models were the default mode, salience, and executive control networks. We also found that cross-network measures of dFC rather than static functional connectivity were better associated with patients' pain, but only in those with NP features. These associations were also more highly and widely associated with measures of trait rather than state pain. Furthermore, greater dynamic connectivity with executive control networks was associated with milder NP, but greater dynamic connectivity with limbic networks was associated with greater NP. Compared with healthy individuals, the dFC features most highly related to trait NP were also more abnormal in patients with greater pain. Our findings indicate that dFC reflects patients' overall pain condition (ie, trait pain), not just their current state, and is impacted by complexities in pain features beyond intensity.

UR - http://www.scopus.com/inward/record.url?scp=85060156845&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060156845&partnerID=8YFLogxK

U2 - 10.1097/j.pain.0000000000001264

DO - 10.1097/j.pain.0000000000001264

M3 - Article

C2 - 29708944

AN - SCOPUS:85060156845

VL - 159

SP - 1764

EP - 1776

JO - Pain

JF - Pain

SN - 0304-3959

IS - 9

ER -