A Biomarker for Discriminating Between Migraine With and Without Aura: Machine Learning on Functional Connectivity on Re
- PDF / 1,168,479 Bytes
- 10 Pages / 593.972 x 792 pts Page_size
- 45 Downloads / 199 Views
Annals of Biomedical Engineering ( 2019) https://doi.org/10.1007/s10439-019-02357-3
Original Article
A Biomarker for Discriminating Between Migraine With and Without Aura: Machine Learning on Functional Connectivity on Resting-State EEGs ALEX FRID ,1 MEIRAV SHOR,2 ALLA SHIFRIN,1,2 DAVID YARNITSKY,1,2 and YELENA GRANOVSKY1,2 1
The Rappaport Faculty of Medicine, Technion – Israel Institute of Technology, Haifa, Israel; and 2Department of Neurology, Rambam Medical Center, Haifa, Israel (Received 6 May 2019; accepted 5 September 2019) Associate Editor Michael Gower oversaw the review of this article.
Abstract—Advanced analyses of electroencephalography (EEG) are rapidly becoming an important tool in understanding the brain’s processing of pain. To date, it appears that none have been explored as a way of distinguishing between migraine patients with aura (MWA) vs. those without aura (MWoA). In this work, we apply a mixture of predictive, e.g., classification methods and attribute-selection techniques, and traditional explanatory, e.g., statistical, analyses on functional connectivity measures extracted from EEG signal acquired from at-rest participants (N = 52) during their interictal period and tested them against the distinction between MWA and MWoA. We show that a functional connectivity metric of EEG data obtained during resting state can serve as a sole biomarker to differentiate between MWA and MWoA. Using the proposed analysis, we not only have been able to present high classification results (average classification of 84.62%) but also to discuss the underlying neurophysiological mechanisms upon which our technique is based. Additionally, a more traditional statistical analysis on the selected features reveals that MWoA patients show higher than average connectivity in the Theta band (p = 0.03) at rest than MWAs. We propose that our data-driven analysis pipeline can be used for resting-EEG analysis in any clinical context. Keywords—EEG functional connectivity analysis, EEG classification, Resting state EEG, Migraine classification, Explanatory machine learning, Biomarker.
Address correspondence to Alex Frid, The Rappaport Faculty of Medicine, Technion – Israel Institute of Technology, Haifa, Israel. Electronic mail: [email protected]
INTRODUCTION Migraine is an incapacitating disorder of neurovascular origin consisting of episodes of headache, accompanied by autonomic and possibly neurological symptoms.21,30 In up to 20% of cases,28 the migraine headache is preceded by an aura, usually a visual illusion, or sensory manifestation, often reported as numbness or tingling in the limbs, face or elsewhere on the body. Many studies describe migraine with aura (MWA) as associated with cortical hyper-responsiveness and a subsequent alteration in the processing of sensory information,2,32 even during the interictal period, as compared to those without aura (MWoA) or healthy individuals.11 More specifically, Sand et al.29 showed that visual cortex excitability seems to be generally increased in MWA as compared to MWoA p
Data Loading...
