Page 258 - MEGIN Book Of Abstracts - 2023

Pain

Resting-state magnetoencephalographic oscillatory 89.1%, AUC: 0.91) in classifying CM from other pain
connectivity to identify patients with chronic disorders (FM in this study). These resting-state magne-
migraine using machine learning (2022) toencephalographic electrophysiological features yield
oscillatory connectivity to identify patients with CM
Hsiao, Fu-Jung; Chen, Wei-Ta; Pan, Li-Ling Hope; Liu, from those with a different type of migraine and pain
Hung-Yu; Wang, Yen-Feng; Chen, Shih-Pin; Lai, Kuan-Lin; disorder, with adequate reliability and generalizability.
Coppola, Gianluca; Wang, Shuu-Jiun
Keywords: Chronic migraine, Machine learning, Magneto-
Brain Research Center, National Yang Ming Chiao Tung Uni- encephalography, Pain disorders, Resting-state oscillatory
versity, Taipei, Taiwan. [email protected]; Department connectivity
of Neurology, Keelung Hospital, Ministry of Health and Wel-
fare, Keelung, Taiwan. [email protected]; Department The journal of headache and pain (2022), Vol. 23, No. 1
of Neurology, Neurological Institute, Taipei Veterans General (36192689) (0 citations)
Hospital, 201, Shih Pai Rd Sec 2, Taipei, Taiwan, 11217; De-
partment of Medico-Surgical Sciences and Biotechnologies,
Sapienza University of Rome Polo Pontino, Latina, Italy A Hidden Markov Model reveals
magnetoencephalography spectral frequency-
ABSTRACT To identify and validate the neural signa- specific abnormalities of brain state power and
tures of resting-state oscillatory connectivity for chronic phase-coupling in neuropathic pain (2022)
migraine (CM), we used machine learning techniques
to classify patients with CM from healthy controls (HC) Fauchon, Camille; Kim, Junseok A; El-Sayed, Rima;
and patients with other pain disorders. The cross- Osborne, Natalie R; Rogachov, Anton; Cheng, Joshua
sectional study obtained resting-state magnetoen- C; Hemington, Kasey S; Bosma, Rachael L; Dunkley,
cephalographic data from 240 participants (70 HC, 100 Benjamin T; Oh, Jiwon; Bhatia, Anuj; Inman, Robert D;
CM, 35 episodic migraine [EM], and 35 fibromyalgia Davis, Karen Deborah
[FM]). Source-based oscillatory connectivity of relevant
cortical regions was calculated to determine intrinsic Division of Brain, Imaging, and Behaviour, Krembil Brain
connectivity at 1-40 Hz. A classification model that Institute, University Health Network, Toronto, ON, M5T 2S8,
employed a support vector machine was developed Canada; Institute of Medical Science, University of Toronto,
using the magnetoencephalographic data to assess the Toronto, ON, M5S 1A8, Canada; Department of Medical Im-
reliability and generalizability of CM identification. In aging, University of Toronto, Toronto, ON, M5T 1W7, Canada;
the findings, the discriminative features that differenti- Div of Neurology, Dept of Medicine, St. Michael's Hospital,
ate CM from HC were principally observed from the Toronto, ON, M5B 1W8, Canada; Department of Anesthesia
functional interactions between salience, sensorimotor, and Pain Medicine, Toronto Western Hospital, and University
and part of the default mode networks. The classifica- of Toronto, Toronto, ON, M5T 2S8, Canada; Division of Immu-
tion model with these features exhibited excellent nology, University of Toronto, Toronto, ON, M5S 1A8, Canada;
performance in distinguishing patients with CM from Department of Surgery, University of Toronto, Toronto, ON,
HC (accuracy ≥ 86.8%, area under the curve (AUC) ≥ 0.9) M5T 1P5, Canada. [email protected]
and from those with EM (accuracy: 94.5%, AUC: 0.96).
The model also achieved high performance (accuracy:

 ontents  Index 237
C