Match!

Are machine learning approaches the future to study patients with migraine

Published on Jan 21, 2020in Neurology8.689
· DOI :10.1212/WNL.0000000000008956
Maria A. Rocca71
Estimated H-index: 71
,
Judith U. Harrer (UniSR: Vita-Salute San Raffaele University)+ 0 AuthorsMassimo Filippi118
Estimated H-index: 118
Abstract
One of the most exciting developments in modern neuroscience has been the expansion of imaging techniques that can provide insights into human brain structures and networks that could be involved in the pathophysiology of diseases. A series of MRI techniques have been extensively applied to the study of patients with migraine. It is now widely accepted that migraine should be viewed as a complex brain network disorder with a strong genetic basis that involves the interplay of multiple neuronal systems to account for the pain and the wide constellation of symptoms characterizing the migraine attack.1 Widespread structural and functional abnormalities in cortical and subcortical areas involved in multisensory processing, including pain, occur in patients with migraine, both in the course of an acute attack and during the interictal phase.2,3 Whether such alterations represent a potential migraine biomarker that can help to discriminate patients with migraine from controls and from patients with other chronic pain conditions is still a matter of debate.
  • References (9)
  • Citations (0)
📖 Papers frequently viewed together
93 Citations
7 Citations
4 Citations
78% of Scinapse members use related papers. After signing in, all features are FREE.
References9
Newest
#1Yiheng TuH-Index: 7
#2Fang ZengH-Index: 14
Last. Courtney LangH-Index: 6
view all 16 authors...
Objective To identify and validate an fMRI-based neural marker for migraine without aura (MwoA) and to examine its association with treatment response. Methods We conducted cross-sectional studies with resting-state fMRI data from 230 participants and machine learning analyses. In studies 1 through 3, we identified, cross-validated, independently validated, and cross-sectionally validated an fMRI-based neural marker for MwoA. In study 4, we assessed the relationship between the neural marker and...
1 CitationsSource
#1Roberta Messina (UniSR: Vita-Salute San Raffaele University)H-Index: 9
#2Massimo Filippi (UniSR: Vita-Salute San Raffaele University)H-Index: 118
Last. Peter J. GoadsbyH-Index: 111
view all 3 authors...
Purpose of reviewPrimary headaches, such as migraine and cluster headache, are one of the most common and disabling neurological diseases worldwide. Neuroimaging studies have changed the way we understand these diseases and have enriched our knowledge of the mechanisms of actions of currently availa
2 CitationsSource
#1Roberta MessinaH-Index: 9
#2Maria A. RoccaH-Index: 71
Last. Massimo FilippiH-Index: 118
view all 7 authors...
Objective To explore cross-sectional and longitudinal gray matter (GM) volume changes in patients with migraine and their association with patients9 clinical characteristics and disease activity. Methods Brain T2-weighted and 3-dimensional T1-weighted scans were acquired from 73 episodic migraineurs and 46 age- and sex-matched nonmigraine controls at baseline. Twenty-four migraineurs and 25 controls agreed to be reexamined after a mean follow-up of 4 years. Using a general linear model and SPM12...
8 CitationsSource
#1Catherine D. Chong (Mayo Clinic)H-Index: 12
#2Nathan Gaw (ASU: Arizona State University)H-Index: 4
Last. Todd J. Schwedt (Mayo Clinic)H-Index: 28
view all 6 authors...
BackgroundThis study used machine-learning techniques to develop discriminative brain-connectivity biomarkers from resting-state functional magnetic resonance neuroimaging (rs-fMRI) data that distinguish between individual migraine patients and healthy controls.MethodsThis study included 58 migraine patients (mean age = 36.3 years; SD = 11.5) and 50 healthy controls (mean age = 35.9 years; SD = 11.0). The functional connections of 33 seeded pain-related regions were used as input for a brain cla...
20 CitationsSource
#1Francesca Puledda ('KCL': King's College London)H-Index: 5
#2Roberta Messina ('KCL': King's College London)H-Index: 9
Last. Peter J. Goadsby ('KCL': King's College London)H-Index: 111
view all 3 authors...
Migraine is a common brain disorder with high disability rates which involves a series of abnormal neuronal networks, interacting at different levels of the central and peripheral nervous system. An increase in the interest around migraine pathophysiology has allowed researchers to unravel certain neurophysiological mechanisms and neurotransmitter involvement culminating in the recent development of novel therapies, which might substantially change the clinical approach to migraine patients. The...
25 CitationsSource
#1Qiongmin Zhang (Sichuan University)H-Index: 2
#2Qizhu Wu (Monash University)H-Index: 1
Last. Qiyong Gong (Sichuan University)H-Index: 62
view all 8 authors...
Magnetic resonance imaging (MRI) is by nature a multi-modality technique that provides complementary information about different aspects of diseases. So far no attempts have been reported to assess the potential of multi-modal MRI in discriminating individuals with and without migraine, so in this study, we proposed a classification approach to examine whether or not the integration of multiple MRI features could improve the classification performance between migraine patients without aura (MWoA...
7 CitationsSource
#1William Pettersson-Yeo ('KCL': King's College London)H-Index: 13
#2Stefania Benetti ('KCL': King's College London)H-Index: 11
Last. Andrea Mechelli ('KCL': King's College London)H-Index: 60
view all 9 authors...
In the pursuit of clinical utility, neuroimaging researchers of psychiatric and neurological illness are increasingly using analyses, such as support vector machine (SVM), that allow inference at the single-subject level. Recent studies employing single-modality data, however, suggest that classification accuracies must be improved for such utility to be realised. One possible solution is to integrate different data types to provide a single combined output classification; either by generating a...
16 CitationsSource
#1Graziella Orrù ('KCL': King's College London)H-Index: 5
#2William Pettersson-Yeo ('KCL': King's College London)H-Index: 13
Last. Andrea Mechelli ('KCL': King's College London)H-Index: 60
view all 5 authors...
Abstract Standard univariate analysis of neuroimaging data has revealed a host of neuroanatomical and functional differences between healthy individuals and patients suffering a wide range of neurological and psychiatric disorders. Significant only at group level however these findings have had limited clinical translation, and recent attention has turned toward alternative forms of analysis, including Support-Vector-Machine (SVM). A type of machine learning, SVM allows categorisation of an indi...
493 CitationsSource
#1Maria A. Rocca (UniSR: Vita-Salute San Raffaele University)H-Index: 71
#2Antonia Ceccarelli (UniSR: Vita-Salute San Raffaele University)H-Index: 22
Last. Massimo Filippi (UniSR: Vita-Salute San Raffaele University)H-Index: 118
view all 9 authors...
Background and Purpose— In migraine patients, functional imaging studies have shown changes in several brain gray matter (GM) regions. However, 1.5-T MRI has failed to detect any structural abnormality of these regions. We used a 3-T MRI scanner and voxel-based morphometry (VBM) to assess whether GM density abnormalities can be seen in patients with migraine with T2-visible abnormalities and to grade their extent. Methods— In 16 migraine patients with T2-visible abnormalities and 15 matched cont...
235 CitationsSource
Cited By0
Newest