Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data
IntroductionMigraine with aura (MwA) is a neurological condition manifested in moderate to severe headaches associated with transient visual and somatosensory symptoms, as well as higher cortical dysfunctions. Considering that about 5% of the world’s population suffers from this condition and manife...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-06-01
|
| Series: | Frontiers in Neurology |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fneur.2023.1106612/full |
| _version_ | 1797794828465995776 |
|---|---|
| author | Katarina Mitrović Igor Petrušić Aleksandra Radojičić Aleksandra Radojičić Marko Daković Andrej Savić |
| author_facet | Katarina Mitrović Igor Petrušić Aleksandra Radojičić Aleksandra Radojičić Marko Daković Andrej Savić |
| author_sort | Katarina Mitrović |
| collection | DOAJ |
| description | IntroductionMigraine with aura (MwA) is a neurological condition manifested in moderate to severe headaches associated with transient visual and somatosensory symptoms, as well as higher cortical dysfunctions. Considering that about 5% of the world’s population suffers from this condition and manifestation could be abundant and characterized by various symptoms, it is of great importance to focus on finding new and advanced techniques for the detection of different phenotypes, which in turn, can allow better diagnosis, classification, and biomarker validation, resulting in tailored treatments of MwA patients.MethodsThis research aimed to test different machine learning techniques to distinguish healthy people from those suffering from MwA, as well as people with simple MwA and those experiencing complex MwA. Magnetic resonance imaging (MRI) post-processed data (cortical thickness, cortical surface area, cortical volume, cortical mean Gaussian curvature, and cortical folding index) was collected from 78 subjects [46 MwA patients (22 simple MwA and 24 complex MwA) and 32 healthy controls] with 340 different features used for the algorithm training.ResultsThe results show that an algorithm based on post-processed MRI data yields a high classification accuracy (97%) of MwA patients and precise distinction between simple MwA and complex MwA with an accuracy of 98%. Additionally, the sets of features relevant to the classification were identified. The feature importance ranking indicates the thickness of the left temporal pole, right lingual gyrus, and left pars opercularis as the most prominent markers for MwA classification, while the thickness of left pericalcarine gyrus and left pars opercularis are proposed as the two most important features for the simple and complex MwA classification.DiscussionThis method shows significant potential in the validation of MwA diagnosis and subtype classification, which can tackle and challenge the current treatments of MwA. |
| first_indexed | 2024-03-13T03:08:42Z |
| format | Article |
| id | doaj.art-47c472905c2b4246a336ff6350a822fd |
| institution | Directory Open Access Journal |
| issn | 1664-2295 |
| language | English |
| last_indexed | 2024-03-13T03:08:42Z |
| publishDate | 2023-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurology |
| spelling | doaj.art-47c472905c2b4246a336ff6350a822fd2023-06-26T16:04:30ZengFrontiers Media S.A.Frontiers in Neurology1664-22952023-06-011410.3389/fneur.2023.11066121106612Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging dataKatarina Mitrović0Igor Petrušić1Aleksandra Radojičić2Aleksandra Radojičić3Marko Daković4Andrej Savić5Department of Information Technologies, Faculty of Technical Sciences in Čačak, University of Kragujevac, Čačak, SerbiaLaboratory for Advanced Analysis of Neuroimages, Faculty of Physical Chemistry, University of Belgrade, Belgrade, SerbiaHeadache Center, Neurology Clinic, Clinical Center of Serbia, Belgrade, SerbiaFaculty of Medicine, University of Belgrade, Belgrade, SerbiaLaboratory for Advanced Analysis of Neuroimages, Faculty of Physical Chemistry, University of Belgrade, Belgrade, SerbiaScience and Research Centre, School of Electrical Engineering, University of Belgrade, Belgrade, SerbiaIntroductionMigraine with aura (MwA) is a neurological condition manifested in moderate to severe headaches associated with transient visual and somatosensory symptoms, as well as higher cortical dysfunctions. Considering that about 5% of the world’s population suffers from this condition and manifestation could be abundant and characterized by various symptoms, it is of great importance to focus on finding new and advanced techniques for the detection of different phenotypes, which in turn, can allow better diagnosis, classification, and biomarker validation, resulting in tailored treatments of MwA patients.MethodsThis research aimed to test different machine learning techniques to distinguish healthy people from those suffering from MwA, as well as people with simple MwA and those experiencing complex MwA. Magnetic resonance imaging (MRI) post-processed data (cortical thickness, cortical surface area, cortical volume, cortical mean Gaussian curvature, and cortical folding index) was collected from 78 subjects [46 MwA patients (22 simple MwA and 24 complex MwA) and 32 healthy controls] with 340 different features used for the algorithm training.ResultsThe results show that an algorithm based on post-processed MRI data yields a high classification accuracy (97%) of MwA patients and precise distinction between simple MwA and complex MwA with an accuracy of 98%. Additionally, the sets of features relevant to the classification were identified. The feature importance ranking indicates the thickness of the left temporal pole, right lingual gyrus, and left pars opercularis as the most prominent markers for MwA classification, while the thickness of left pericalcarine gyrus and left pars opercularis are proposed as the two most important features for the simple and complex MwA classification.DiscussionThis method shows significant potential in the validation of MwA diagnosis and subtype classification, which can tackle and challenge the current treatments of MwA.https://www.frontiersin.org/articles/10.3389/fneur.2023.1106612/fullmigraine with auramachine learningmagnetic resonance imagingartificial intelligenceclassification |
| spellingShingle | Katarina Mitrović Igor Petrušić Aleksandra Radojičić Aleksandra Radojičić Marko Daković Andrej Savić Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data Frontiers in Neurology migraine with aura machine learning magnetic resonance imaging artificial intelligence classification |
| title | Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| title_full | Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| title_fullStr | Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| title_full_unstemmed | Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| title_short | Migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| title_sort | migraine with aura detection and subtype classification using machine learning algorithms and morphometric magnetic resonance imaging data |
| topic | migraine with aura machine learning magnetic resonance imaging artificial intelligence classification |
| url | https://www.frontiersin.org/articles/10.3389/fneur.2023.1106612/full |
| work_keys_str_mv | AT katarinamitrovic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata AT igorpetrusic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata AT aleksandraradojicic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata AT aleksandraradojicic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata AT markodakovic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata AT andrejsavic migrainewithauradetectionandsubtypeclassificationusingmachinelearningalgorithmsandmorphometricmagneticresonanceimagingdata |