Altered brainstem-cortex activation and interaction in migraine patients: somatosensory evoked EEG responses with machine learning.
Brainstem
EEG
Insula
Machine learning
Migraine
Primary motor cortex
Primary somatosensory cortex
Sensory processing
Spectral Granger causality analysis
Support vector machine
Journal
The journal of headache and pain
ISSN: 1129-2377
Titre abrégé: J Headache Pain
Pays: England
ID NLM: 100940562
Informations de publication
Date de publication:
28 Oct 2024
28 Oct 2024
Historique:
received:
19
09
2024
accepted:
18
10
2024
medline:
29
10
2024
pubmed:
29
10
2024
entrez:
29
10
2024
Statut:
epublish
Résumé
To gain a comprehensive understanding of the altered sensory processing in patients with migraine, in this study, we developed an electroencephalography (EEG) protocol for examining brainstem and cortical responses to sensory stimulation. Furthermore, machine learning techniques were employed to identify neural signatures from evoked brainstem-cortex activation and their interactions, facilitating the identification of the presence and subtype of migraine. This study analysed 1,000-epoch-averaged somatosensory evoked responses from 342 participants, comprising 113 healthy controls (HCs), 106 patients with chronic migraine (CM), and 123 patients with episodic migraine (EM). Activation amplitude and effective connectivity were obtained using weighted minimum norm estimates with spectral Granger causality analysis. This study used support vector machine algorithms to develop classification models; multimodal data (amplitude, connectivity, and scores of psychometric assessments) were applied to assess the reliability and generalisability of the identification results from the classification models. The findings revealed that patients with migraine exhibited reduced amplitudes for responses in both the brainstem and cortical regions and increased effective connectivity between these regions in the gamma and high-gamma frequency bands. The classification model with characteristic features performed well in distinguishing patients with CM from HCs, achieving an accuracy of 81.8% and an area under the curve (AUC) of 0.86 during training and an accuracy of 76.2% and an AUC of 0.89 during independent testing. Similarly, the model effectively identified patients with EM, with an accuracy of 77.5% and an AUC of 0.84 during training and an accuracy of 87% and an AUC of 0.88 during independent testing. Additionally, the model successfully differentiated patients with CM from patients with EM, with an accuracy of 70.5% and an AUC of 0.73 during training and an accuracy of 72.7% and an AUC of 0.74 during independent testing. Altered brainstem-cortex activation and interaction are characteristic of the abnormal sensory processing in migraine. Combining evoked activity analysis with machine learning offers a reliable and generalisable tool for identifying patients with migraine and for assessing the severity of their condition. Thus, this approach is an effective and rapid diagnostic tool for clinicians.
Sections du résumé
BACKGROUND
BACKGROUND
To gain a comprehensive understanding of the altered sensory processing in patients with migraine, in this study, we developed an electroencephalography (EEG) protocol for examining brainstem and cortical responses to sensory stimulation. Furthermore, machine learning techniques were employed to identify neural signatures from evoked brainstem-cortex activation and their interactions, facilitating the identification of the presence and subtype of migraine.
METHODS
METHODS
This study analysed 1,000-epoch-averaged somatosensory evoked responses from 342 participants, comprising 113 healthy controls (HCs), 106 patients with chronic migraine (CM), and 123 patients with episodic migraine (EM). Activation amplitude and effective connectivity were obtained using weighted minimum norm estimates with spectral Granger causality analysis. This study used support vector machine algorithms to develop classification models; multimodal data (amplitude, connectivity, and scores of psychometric assessments) were applied to assess the reliability and generalisability of the identification results from the classification models.
RESULTS
RESULTS
The findings revealed that patients with migraine exhibited reduced amplitudes for responses in both the brainstem and cortical regions and increased effective connectivity between these regions in the gamma and high-gamma frequency bands. The classification model with characteristic features performed well in distinguishing patients with CM from HCs, achieving an accuracy of 81.8% and an area under the curve (AUC) of 0.86 during training and an accuracy of 76.2% and an AUC of 0.89 during independent testing. Similarly, the model effectively identified patients with EM, with an accuracy of 77.5% and an AUC of 0.84 during training and an accuracy of 87% and an AUC of 0.88 during independent testing. Additionally, the model successfully differentiated patients with CM from patients with EM, with an accuracy of 70.5% and an AUC of 0.73 during training and an accuracy of 72.7% and an AUC of 0.74 during independent testing.
CONCLUSION
CONCLUSIONS
Altered brainstem-cortex activation and interaction are characteristic of the abnormal sensory processing in migraine. Combining evoked activity analysis with machine learning offers a reliable and generalisable tool for identifying patients with migraine and for assessing the severity of their condition. Thus, this approach is an effective and rapid diagnostic tool for clinicians.
Identifiants
pubmed: 39468471
doi: 10.1186/s10194-024-01892-2
pii: 10.1186/s10194-024-01892-2
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
185Subventions
Organisme : Ministry of Science and Technology, Taiwan
ID : 110-2321-B-010-005, 111-2321-B-A49-004, 109-2221-E-003-MY2, and 111-2221-E-A49-038
Organisme : Ministry of Science and Technology, Taiwan
ID : 110-2321-B-010-005, 111-2321-B-A49-004, 109-2221-E-003-MY2, and 111-2221-E-A49-038
Organisme : National Science and Technology Council, Taiwan
ID : 112-2321-B-075-007, 113-2321-B-A49-017, and 112-2221-E-A49 -012 -MY2
Organisme : National Science and Technology Council, Taiwan
ID : 112-2321-B-075-007, 113-2321-B-A49-017, and 112-2221-E-A49 -012 -MY2
Informations de copyright
© 2024. The Author(s).
Références
Stovner LJ, Nichols E, Steiner TJ, Abd-Allah F, Abdelalim A, Al-Raddadi RM, Ansha MG, Barac A, Bensenor IM, Doan LP (2018) Global, regional, and national burden of migraine and tension-type headache, 1990–2016: a systematic analysis for the global burden of Disease Study 2016. Lancet Neurol 17:954–976
doi: 10.1016/S1474-4422(18)30322-3
Headache Classification Committee of the International Headache Society (IHS) (2018) The International Classification of Headache Disorders, 3rd edition. Cephalalgia 38:1–211
Ashina M, Katsarava Z, Do TP, Buse DC, Pozo-Rosich P, Ozge A, Krymchantowski AV, Lebedeva ER, Ravishankar K, Yu S, Sacco S, Ashina S, Younis S, Steiner TJ, Lipton RB (2021) Migraine: epidemiology and systems of care. Lancet 397:1485–1495
pubmed: 33773613
doi: 10.1016/S0140-6736(20)32160-7
Ashina M (2020) Migraine. N Engl J Med 383:1866–1876
pubmed: 33211930
doi: 10.1056/NEJMra1915327
Dodick DW (2018) Migraine. Lancet 391:1315–1330
pubmed: 29523342
doi: 10.1016/S0140-6736(18)30478-1
de Tommaso M, Ambrosini A, Brighina F, Coppola G, Perrotta A, Pierelli F, Sandrini G, Valeriani M, Marinazzo D, Stramaglia S, Schoenen J (2014) Altered processing of sensory stimuli in patients with migraine. Nat Rev Neurol 10:144–155
pubmed: 24535465
doi: 10.1038/nrneurol.2014.14
Akerman S, Holland PR, Goadsby PJ (2011) Diencephalic and brainstem mechanisms in migraine. Nat Rev Neurosci 12:570–584
pubmed: 21931334
doi: 10.1038/nrn3057
Coppola G, Di Lorenzo C, Parisi V, Lisicki M, Serrao M, Pierelli F (2019) Clinical neurophysiology of migraine with aura. J Headache Pain 20:42
pubmed: 31035929
pmcid: 6734510
doi: 10.1186/s10194-019-0997-9
Hsiao FJ, Chen WT, Wu YT, Pan LH, Wang YF, Chen SP, Lai KL, Coppola G, Wang SJ (2023) Characteristic oscillatory brain networks for predicting patients with chronic migraine. J Headache Pain 24:139
pubmed: 37848845
pmcid: 10583316
doi: 10.1186/s10194-023-01677-z
Ashina M, Terwindt GM, Al-Karagholi MA, de Boer I, Lee MJ, Hay DL, Schulte LH, Hadjikhani N, Sinclair AJ, Ashina H, Schwedt TJ, Goadsby PJ (2021) Migraine: disease characterisation, biomarkers, and precision medicine. Lancet 397:1496–1504
pubmed: 33773610
doi: 10.1016/S0140-6736(20)32162-0
Hsiao FJ, Chen WT, Pan LH, Liu HY, Wang YF, Chen SP, Lai KL, Coppola G, Wang SJ (2022) Dynamic brainstem and somatosensory cortical excitability during migraine cycles. J Headache Pain 23:21
pubmed: 35123411
pmcid: 8903675
doi: 10.1186/s10194-022-01392-1
Zigmond AS, Snaith RP (1983) The hospital anxiety and depression scale. Acta Psychiatr Scand 67:361–370
pubmed: 6880820
doi: 10.1111/j.1600-0447.1983.tb09716.x
Hung PH, Fuh JL, Wang SJ (2006) Validity, reliability and application of the Taiwan version of the migraine disability assessment questionnaire. J Formos Med Assoc 105:563–568
pubmed: 16877236
doi: 10.1016/S0929-6646(09)60151-0
Chen WT, Hsiao FJ, Ko YC, Liu HY, Wang PN, Fuh JL, Lin YY, Wang SJ (2018) Comparison of somatosensory cortex excitability between migraine and strict-criteria tension-type headache: a magnetoencephalographic study. Pain 159:793–803
pubmed: 29319611
doi: 10.1097/j.pain.0000000000001151
Hsiao FJ, Wang SJ, Lin YY, Fuh JL, Ko YC, Wang PN, Chen WT (2018) Somatosensory gating is altered and associated with migraine chronification: a magnetoencephalographic study. Cephalalgia 38:744–753
pubmed: 28540738
doi: 10.1177/0333102417712718
Attal Y, Bhattacharjee M, Yelnik J, Cottereau B, Lefevre J, Okada Y, Bardinet E, Chupin M, Baillet S (2007) Modeling and detecting deep brain activity with MEG & EEG. Annu Int Conf IEEE Eng Med Biol Soc 2007:4937–4940
pubmed: 18003114
Hsiao FJ, Wang SJ, Lin YY, Fuh JL, Ko YC, Wang PN, Chen WT (2017) Altered insula-default mode network connectivity in fibromyalgia: a resting-state magnetoencephalographic study. J Headache Pain 18:89
pubmed: 28831711
pmcid: 5567574
doi: 10.1186/s10194-017-0799-x
Hamalainen MS, Ilmoniemi RJ (1994) Interpreting magnetic fields of the brain: minimum norm estimates. Med Biol Eng Comput 32:35–42
pubmed: 8182960
doi: 10.1007/BF02512476
Attal Y, Schwartz D (2013) Assessment of subcortical source localization using deep brain activity imaging model with minimum norm operators: a MEG study. PLoS ONE 8:e59856
pubmed: 23527277
pmcid: 3603889
doi: 10.1371/journal.pone.0059856
Gramfort A, Papadopoulo T, Olivi E, Clerc M (2010) OpenMEEG: opensource software for quasistatic bioelectromagnetics. Biomed Eng Online 9:45
pubmed: 20819204
pmcid: 2949879
doi: 10.1186/1475-925X-9-45
Granger CWJ (1969) Investigating causal relations by Econometric Models and cross-spectral methods. Econometrica 37:424–438
doi: 10.2307/1912791
Geweke JF (1984) Measures of conditional Linear-Dependence and Feedback between Time-Series. J Am Stat Assoc 79:907–915
doi: 10.1080/01621459.1984.10477110
Tadel F, Baillet S, Mosher JC, Pantazis D, Leahy RM (2011) Brainstorm: a user-friendly application for MEG/EEG analysis. Comput Intell Neurosci 2011:879716
pubmed: 21584256
pmcid: 3090754
doi: 10.1155/2011/879716
Hsiao FJ, Chen WT, Pan LH, Liu HY, Wang YF, Chen SP, Lai KL, Coppola G, Wang SJ (2022) Resting-state magnetoencephalographic oscillatory connectivity to identify patients with chronic migraine using machine learning. J Headache Pain 23:130
pubmed: 36192689
pmcid: 9531441
doi: 10.1186/s10194-022-01500-1
Hsiao FJ, Chen WT, Wang YF, Chen SP, Lai KL, Coppola G, Wang SJ (2023) Identification of patients with chronic migraine by using sensory-evoked oscillations from the electroencephalogram classifier. Cephalalgia 43:3331024231176074
pubmed: 37194198
doi: 10.1177/03331024231176074
Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Proceedings of the 31st international conference on neural information processing systems, p. 4768–4777
Maccora S, Bolognini N, Cosentino G, Baschi R, Vallar G, Fierro B, Brighina F (2020) Multisensorial Perception in Chronic Migraine and the role of medication overuse. J Pain 21:919–929
pubmed: 31904501
doi: 10.1016/j.jpain.2019.12.005
Sebastianelli G, Abagnale C, Casillo F, Cioffi E, Parisi V, Di Lorenzo C, Serrao M, Porcaro C, Schoenen J, Coppola G (2022) Bimodal sensory integration in migraine: a study of the effect of visual stimulation on somatosensory evoked cortical responses. Cephalalgia 42:654–662
pubmed: 35166155
doi: 10.1177/03331024221075073
Demarquay G, Royet JP, Mick G, Ryvlin P (2008) Olfactory hypersensitivity in migraineurs: a H(2)(15)O-PET study. Cephalalgia 28:1069–1080
pubmed: 18727640
doi: 10.1111/j.1468-2982.2008.01672.x
Marciszewski KK, Meylakh N, Di Pietro F, Mills EP, Macefield VG, Macey PM, Henderson LA (2018) Changes in Brainstem Pain Modulation Circuitry function over the Migraine cycle. J Neurosci 38:10479–10488
pubmed: 30341182
pmcid: 6596255
doi: 10.1523/JNEUROSCI.1088-18.2018
Porcaro C, Di Lorenzo G, Seri S, Pierelli F, Tecchio F, Coppola G (2017) Impaired brainstem and thalamic high-frequency oscillatory EEG activity in migraine between attacks. Cephalalgia 37:915–926
pubmed: 27358281
doi: 10.1177/0333102416657146
Borsook D, Veggeberg R, Erpelding N, Borra R, Linnman C, Burstein R, Becerra L (2016) The Insula: a hub of activity in Migraine. Neuroscientist 22:632–652
pubmed: 26290446
doi: 10.1177/1073858415601369
Christensen RH, Ashina H, Al-Khazali HM, Zhang Y, Tolnai D, Poulsen AH, Cagol A, Hadjikhani N, Granziera C, Amin FM, Ashina M (2024) Differences in cortical morphology in people with and without migraine: a Registry for Migraine (REFORM) MRI study. Neurology 102:e209305
pubmed: 38630960
pmcid: 11175630
doi: 10.1212/WNL.0000000000209305
Chen H, Qi G, Zhang Y, Huang Y, Zhang S, Yang D, He J, Mu L, Zhou L, Zeng M (2021) Altered dynamic amplitude of low-frequency fluctuations in patients with Migraine without Aura. Front Hum Neurosci 15:636472
pubmed: 33679354
pmcid: 7928334
doi: 10.3389/fnhum.2021.636472
Coppola G, Vandenheede M, Di Clemente L, Ambrosini A, Fumal A, De Pasqua V, Schoenen J (2005) Somatosensory evoked high-frequency oscillations reflecting thalamo-cortical activity are decreased in migraine patients between attacks. Brain 128:98–103
pubmed: 15563513
doi: 10.1093/brain/awh334
Moulton EA, Burstein R, Tully S, Hargreaves R, Becerra L, Borsook D (2008) Interictal dysfunction of a brainstem descending modulatory center in migraine patients. PLoS ONE 3:e3799
pubmed: 19030105
pmcid: 2582961
doi: 10.1371/journal.pone.0003799
Russo A, Tessitore A, Esposito F, Marcuccio L, Giordano A, Conforti R, Truini A, Paccone A, d’Onofrio F, Tedeschi G (2012) Pain processing in patients with migraine: an event-related fMRI study during trigeminal nociceptive stimulation. J Neurol 259:1903–1912
pubmed: 22349864
doi: 10.1007/s00415-012-6438-1
Schwedt TJ, Chong CD, Chiang CC, Baxter L, Schlaggar BL, Dodick DW (2014) Enhanced pain-induced activity of pain-processing regions in a case-control study of episodic migraine. Cephalalgia 34:947–958
pubmed: 24627432
pmcid: 4163130
doi: 10.1177/0333102414526069
Coppola G, Curra A, Serrao M, Di Lorenzo C, Gorini M, Porretta E, Alibardi A, Parisi V, Pierelli F (2010) Lack of cold pressor test-induced effect on visual-evoked potentials in migraine. J Headache Pain 11:115–121
pubmed: 20012123
doi: 10.1007/s10194-009-0177-4
Schoenen J (1996) Deficient habituation of evoked cortical potentials in migraine: a link between brain biology, behavior and trigeminovascular activation? Biomed Pharmacother 50:71–78
pubmed: 8761712
doi: 10.1016/0753-3322(96)84716-0
Garcia RG, Lin RL, Lee J, Kim J, Barbieri R, Sclocco R, Wasan AD, Edwards RR, Rosen BR, Hadjikhani N, Napadow V (2017) Modulation of brainstem activity and connectivity by respiratory-gated auricular vagal afferent nerve stimulation in migraine patients. Pain 158:1461–1472
pubmed: 28541256
pmcid: 5517046
doi: 10.1097/j.pain.0000000000000930
Liu K, Cheng J, Cao Y, Chen K, Li Y, Zhang X, Dong L, Wang Z, Liu X (2023) Abnormally increased effective connectivity of the Periaqueductal Gray in Migraine without Aura patients. Clin J Pain 39:175–179
pubmed: 36943161
doi: 10.1097/AJP.0000000000001099
Hougaard A, Amin FM, Larsson HB, Rostrup E, Ashina M (2017) Increased intrinsic brain connectivity between pons and somatosensory cortex during attacks of migraine with aura. Hum Brain Mapp 38:2635–2642
pubmed: 28240389
pmcid: 6867076
doi: 10.1002/hbm.23548
Desmedt JE, Cheron G (1980) Somatosensory evoked potentials to finger stimulation in healthy octogenarians and in young adults: wave forms, scalp topography and transit times of parietal and frontal components. Electroencephalogr Clin Neurophysiol 50:404–425
pubmed: 6160983
doi: 10.1016/0013-4694(80)90007-3
Coppola G, Ambrosini A, Di Clemente L, Magis D, Fumal A, Gerard P, Pierelli F, Schoenen J (2007) Interictal abnormalities of gamma band activity in visual evoked responses in migraine: an indication of thalamocortical dysrhythmia? Cephalalgia 27:1360–1367
pubmed: 17986271
doi: 10.1111/j.1468-2982.2007.01466.x
Llinas R, Urbano FJ, Leznik E, Ramirez RR, van Marle HJ (2005) Rhythmic and dysrhythmic thalamocortical dynamics: GABA systems and the edge effect. Trends Neurosci 28:325–333
pubmed: 15927689
doi: 10.1016/j.tins.2005.04.006
Llinas RR, Steriade M (2006) Bursting of thalamic neurons and states of vigilance. J Neurophysiol 95:3297–3308
pubmed: 16554502
doi: 10.1152/jn.00166.2006
Coppola G, Di Renzo A, Petolicchio B, Tinelli E, Di Lorenzo C, Parisi V, Serrao M, Calistri V, Tardioli S, Cartocci G, Schoenen J, Caramia F, Di Piero V, Pierelli F (2019) Aberrant interactions of cortical networks in chronic migraine: a resting-state fMRI study. Neurology 92:e2550–e2558
pubmed: 31053665
doi: 10.1212/WNL.0000000000007577
Lefaucheur JP, Drouot X, Keravel Y, Nguyen JP (2001) Pain relief induced by repetitive transcranial magnetic stimulation of precentral cortex. NeuroReport 12:2963–2965
pubmed: 11588611
doi: 10.1097/00001756-200109170-00041
Zhu B, Coppola G, Shoaran M (2019) Migraine classification using somatosensory evoked potentials. Cephalalgia 39:1143–1155
pubmed: 30913908
doi: 10.1177/0333102419839975
Puledda F, Vigano A, Sebastianelli G, Parisi V, Hsiao FJ, Wang SJ, Chen WT, Massimini M, Coppola G (2023) Electrophysiological findings in migraine may reflect abnormal synaptic plasticity mechanisms: a narrative review. Cephalalgia 43:3331024231195780
pubmed: 37622421
doi: 10.1177/03331024231195780
Tu Y, Zeng F, Lan L, Li Z, Maleki N, Liu B, Chen J, Wang C, Park J, Lang C, Yujie G, Liu M, Fu Z, Zhang Z, Liang F, Kong J (2020) An fMRI-based neural marker for migraine without aura. Neurology 94:e741–e751
pubmed: 31964691
pmcid: 7176301
doi: 10.1212/WNL.0000000000008962