Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved]
Background. Chronic pain is a common, often disabling condition thought to involve a combination of peripheral and central neurobiological factors. However, the extent and nature of changes in the brain is poorly understood. Methods. We investigated brain network architecture using resting-state fMR...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wellcome
2018-03-01
|
| Series: | Wellcome Open Research |
| Online Access: | https://wellcomeopenresearch.org/articles/3-19/v1 |
| _version_ | 1819327354645774336 |
|---|---|
| author | Hiroaki Mano Gopal Kotecha Kenji Leibnitz Takashi Matsubara Aya Nakae Nicholas Shenker Masahiko Shibata Valerie Voon Wako Yoshida Michael Lee Toshio Yanagida Mitsuo Kawato Maria Joao Rosa Ben Seymour |
| author_facet | Hiroaki Mano Gopal Kotecha Kenji Leibnitz Takashi Matsubara Aya Nakae Nicholas Shenker Masahiko Shibata Valerie Voon Wako Yoshida Michael Lee Toshio Yanagida Mitsuo Kawato Maria Joao Rosa Ben Seymour |
| author_sort | Hiroaki Mano |
| collection | DOAJ |
| description | Background. Chronic pain is a common, often disabling condition thought to involve a combination of peripheral and central neurobiological factors. However, the extent and nature of changes in the brain is poorly understood. Methods. We investigated brain network architecture using resting-state fMRI data in chronic back pain patients in the UK and Japan (41 patients, 56 controls), as well as open data from USA. We applied machine learning and deep learning (conditional variational autoencoder architecture) methods to explore classification of patients/controls based on network connectivity. We then studied the network topology of the data, and developed a multislice modularity method to look for consensus evidence of modular reorganisation in chronic back pain. Results. Machine learning and deep learning allowed reliable classification of patients in a third, independent open data set with an accuracy of 63%, with 68% in cross validation of all data. We identified robust evidence of network hub disruption in chronic pain, most consistently with respect to clustering coefficient and betweenness centrality. We found a consensus pattern of modular reorganisation involving extensive, bilateral regions of sensorimotor cortex, and characterised primarily by negative reorganisation - a tendency for sensorimotor cortex nodes to be less inclined to form pairwise modular links with other brain nodes. In contrast, intraparietal sulcus displayed a propensity towards positive modular reorganisation, suggesting that it might have a role in forming modules associated with the chronic pain state. Conclusion. The results provide evidence of consistent and characteristic brain network changes in chronic pain, characterised primarily by extensive reorganisation of the network architecture of the sensorimotor cortex. |
| first_indexed | 2024-12-24T13:09:31Z |
| format | Article |
| id | doaj.art-5b28abdeead14ed3b2d109a2bc6c6e34 |
| institution | Directory Open Access Journal |
| issn | 2398-502X |
| language | English |
| last_indexed | 2024-12-24T13:09:31Z |
| publishDate | 2018-03-01 |
| publisher | Wellcome |
| record_format | Article |
| series | Wellcome Open Research |
| spelling | doaj.art-5b28abdeead14ed3b2d109a2bc6c6e342022-12-21T16:53:55ZengWellcomeWellcome Open Research2398-502X2018-03-01310.12688/wellcomeopenres.14069.115303Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved]Hiroaki Mano0Gopal Kotecha1Kenji Leibnitz2Takashi Matsubara3Aya Nakae4Nicholas Shenker5Masahiko Shibata6Valerie Voon7Wako Yoshida8Michael Lee9Toshio Yanagida10Mitsuo Kawato11Maria Joao Rosa12Ben Seymour13Center for Information and Neural Networks, National Institute of Information and Communications Technology, Osaka, JapanCambridge University Hospitals NHS Foundation Trust, Cambridge, UKCenter for Information and Neural Networks, National Institute of Information and Communications Technology, Osaka, JapanGraduate School of System Informatics, Kobe University, Kobe, JapanOsaka University School of Medicine, Osaka, JapanCambridge University Hospitals NHS Foundation Trust, Cambridge, UKOsaka University School of Medicine, Osaka, JapanSchool of Clinical Medicine, University of Cambridge, Cambridge, UKAdvanced Telecommunications Research Center International, Kyoto, JapanSchool of Clinical Medicine, University of Cambridge, Cambridge, UKCenter for Information and Neural Networks, National Institute of Information and Communications Technology, Osaka, JapanAdvanced Telecommunications Research Center International, Kyoto, JapanMax-Planck UCL Centre for Computational Psychiatry and Ageing Research, University College London, London, UKCenter for Information and Neural Networks, National Institute of Information and Communications Technology, Osaka, JapanBackground. Chronic pain is a common, often disabling condition thought to involve a combination of peripheral and central neurobiological factors. However, the extent and nature of changes in the brain is poorly understood. Methods. We investigated brain network architecture using resting-state fMRI data in chronic back pain patients in the UK and Japan (41 patients, 56 controls), as well as open data from USA. We applied machine learning and deep learning (conditional variational autoencoder architecture) methods to explore classification of patients/controls based on network connectivity. We then studied the network topology of the data, and developed a multislice modularity method to look for consensus evidence of modular reorganisation in chronic back pain. Results. Machine learning and deep learning allowed reliable classification of patients in a third, independent open data set with an accuracy of 63%, with 68% in cross validation of all data. We identified robust evidence of network hub disruption in chronic pain, most consistently with respect to clustering coefficient and betweenness centrality. We found a consensus pattern of modular reorganisation involving extensive, bilateral regions of sensorimotor cortex, and characterised primarily by negative reorganisation - a tendency for sensorimotor cortex nodes to be less inclined to form pairwise modular links with other brain nodes. In contrast, intraparietal sulcus displayed a propensity towards positive modular reorganisation, suggesting that it might have a role in forming modules associated with the chronic pain state. Conclusion. The results provide evidence of consistent and characteristic brain network changes in chronic pain, characterised primarily by extensive reorganisation of the network architecture of the sensorimotor cortex.https://wellcomeopenresearch.org/articles/3-19/v1 |
| spellingShingle | Hiroaki Mano Gopal Kotecha Kenji Leibnitz Takashi Matsubara Aya Nakae Nicholas Shenker Masahiko Shibata Valerie Voon Wako Yoshida Michael Lee Toshio Yanagida Mitsuo Kawato Maria Joao Rosa Ben Seymour Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] Wellcome Open Research |
| title | Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] |
| title_full | Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] |
| title_fullStr | Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] |
| title_full_unstemmed | Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] |
| title_short | Classification and characterisation of brain network changes in chronic back pain: A multicenter study [version 1; referees: 2 approved] |
| title_sort | classification and characterisation of brain network changes in chronic back pain a multicenter study version 1 referees 2 approved |
| url | https://wellcomeopenresearch.org/articles/3-19/v1 |
| work_keys_str_mv | AT hiroakimano classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT gopalkotecha classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT kenjileibnitz classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT takashimatsubara classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT ayanakae classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT nicholasshenker classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT masahikoshibata classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT valerievoon classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT wakoyoshida classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT michaellee classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT toshioyanagida classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT mitsuokawato classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT mariajoaorosa classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved AT benseymour classificationandcharacterisationofbrainnetworkchangesinchronicbackpainamulticenterstudyversion1referees2approved |