The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache
BackgroundPost-traumatic headache (PTH) and migraine often have similar phenotypes. The objective of this exploratory study was to develop classification models to differentiate persistent PTH (PPTH) from migraine using clinical data and magnetic resonance imaging (MRI) measures of brain structure a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-01-01
|
| Series: | Frontiers in Pain Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpain.2022.1012831/full |
| _version_ | 1797956848235577344 |
|---|---|
| author | Gina Dumkrieger Catherine D Chong Katherine Ross Visar Berisha Todd J Schwedt |
| author_facet | Gina Dumkrieger Catherine D Chong Katherine Ross Visar Berisha Todd J Schwedt |
| author_sort | Gina Dumkrieger |
| collection | DOAJ |
| description | BackgroundPost-traumatic headache (PTH) and migraine often have similar phenotypes. The objective of this exploratory study was to develop classification models to differentiate persistent PTH (PPTH) from migraine using clinical data and magnetic resonance imaging (MRI) measures of brain structure and functional connectivity (fc).MethodsThirty-four individuals with migraine and 48 individuals with PPTH attributed to mild TBI were included. All individuals completed questionnaires assessing headache characteristics, mood, sensory hypersensitivities, and cognitive function and underwent brain structural and functional imaging during the same study visit. Clinical features, structural and functional resting-state measures were included as potential variables. Classifiers using ridge logistic regression of principal components were fit on the data. Average accuracy was calculated using leave-one-out cross-validation. Models were fit with and without fc data. The importance of specific variables to the classifier were examined.ResultsWith internal variable selection and principal components creation the average accuracy was 72% with fc data and 63.4% without fc data. This classifier with fc data identified individuals with PPTH and individuals with migraine with equal accuracy.ConclusionMultivariate models based on clinical characteristics, fc, and brain structural data accurately classify and differentiate PPTH vs. migraine suggesting differences in the neuromechanism and clinical features underlying both headache disorders. |
| first_indexed | 2024-04-10T23:55:14Z |
| format | Article |
| id | doaj.art-0e011c8560b94507b340340bfb593110 |
| institution | Directory Open Access Journal |
| issn | 2673-561X |
| language | English |
| last_indexed | 2024-04-10T23:55:14Z |
| publishDate | 2023-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Pain Research |
| spelling | doaj.art-0e011c8560b94507b340340bfb5931102023-01-10T13:45:49ZengFrontiers Media S.A.Frontiers in Pain Research2673-561X2023-01-01310.3389/fpain.2022.10128311012831The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headacheGina Dumkrieger0Catherine D Chong1Katherine Ross2Visar Berisha3Todd J Schwedt4Department of Neurology, Mayo Clinic Arizona, Phoenix, AZ, United StatesDepartment of Neurology, Mayo Clinic Arizona, Phoenix, AZ, United StatesPhoenix VA health care system, Veterans Health Administration, Phoenix, AZ, United StatesDepartment of Speech and Hearing Science and School of Electrical Computer and Energy Engineering, Arizona State University, Tempe, AZ, United StatesDepartment of Neurology, Mayo Clinic Arizona, Phoenix, AZ, United StatesBackgroundPost-traumatic headache (PTH) and migraine often have similar phenotypes. The objective of this exploratory study was to develop classification models to differentiate persistent PTH (PPTH) from migraine using clinical data and magnetic resonance imaging (MRI) measures of brain structure and functional connectivity (fc).MethodsThirty-four individuals with migraine and 48 individuals with PPTH attributed to mild TBI were included. All individuals completed questionnaires assessing headache characteristics, mood, sensory hypersensitivities, and cognitive function and underwent brain structural and functional imaging during the same study visit. Clinical features, structural and functional resting-state measures were included as potential variables. Classifiers using ridge logistic regression of principal components were fit on the data. Average accuracy was calculated using leave-one-out cross-validation. Models were fit with and without fc data. The importance of specific variables to the classifier were examined.ResultsWith internal variable selection and principal components creation the average accuracy was 72% with fc data and 63.4% without fc data. This classifier with fc data identified individuals with PPTH and individuals with migraine with equal accuracy.ConclusionMultivariate models based on clinical characteristics, fc, and brain structural data accurately classify and differentiate PPTH vs. migraine suggesting differences in the neuromechanism and clinical features underlying both headache disorders.https://www.frontiersin.org/articles/10.3389/fpain.2022.1012831/fullpost-traumatic headache (PTH)migrainefMRIclassificationmachine learning |
| spellingShingle | Gina Dumkrieger Catherine D Chong Katherine Ross Visar Berisha Todd J Schwedt The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache Frontiers in Pain Research post-traumatic headache (PTH) migraine fMRI classification machine learning |
| title | The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache |
| title_full | The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache |
| title_fullStr | The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache |
| title_full_unstemmed | The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache |
| title_short | The value of brain MRI functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post-traumatic headache |
| title_sort | value of brain mri functional connectivity data in a machine learning classifier for distinguishing migraine from persistent post traumatic headache |
| topic | post-traumatic headache (PTH) migraine fMRI classification machine learning |
| url | https://www.frontiersin.org/articles/10.3389/fpain.2022.1012831/full |
| work_keys_str_mv | AT ginadumkrieger thevalueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT catherinedchong thevalueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT katherineross thevalueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT visarberisha thevalueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT toddjschwedt thevalueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT ginadumkrieger valueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT catherinedchong valueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT katherineross valueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT visarberisha valueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache AT toddjschwedt valueofbrainmrifunctionalconnectivitydatainamachinelearningclassifierfordistinguishingmigrainefrompersistentposttraumaticheadache |