Artificial neural networks applied to somatosensory evoked potentials for migraine classification
Abstract Background Finding a biomarker to diagnose migraine remains a significant challenge in the headache field. Migraine patients exhibit dynamic and recurrent alterations in the brainstem-thalamo-cortical loop, including reduced thalamocortical activity and abnormal habituation during the inter...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-04-01
|
| Series: | The Journal of Headache and Pain |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s10194-025-01989-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850153514168221696 |
|---|---|
| author | Gabriele Sebastianelli Daniele Secci Francesco Casillo Chiara Abagnale Cherubino Di Lorenzo Mariano Serrao Shuu-Jiun Wang Fu-Jung Hsiao Gianluca Coppola |
| author_facet | Gabriele Sebastianelli Daniele Secci Francesco Casillo Chiara Abagnale Cherubino Di Lorenzo Mariano Serrao Shuu-Jiun Wang Fu-Jung Hsiao Gianluca Coppola |
| author_sort | Gabriele Sebastianelli |
| collection | DOAJ |
| description | Abstract Background Finding a biomarker to diagnose migraine remains a significant challenge in the headache field. Migraine patients exhibit dynamic and recurrent alterations in the brainstem-thalamo-cortical loop, including reduced thalamocortical activity and abnormal habituation during the interictal phase. Although these insights into migraine pathophysiology have been valuable, they are not currently used in clinical practice. This study aims to evaluate the potential of Artificial Neural Networks (ANNs) in distinguishing migraine patients from healthy individuals using neurophysiological recordings. Methods We recorded Somatosensory Evoked Potentials (SSEPs) to gather electrophysiological data from low- and high-frequency signal bands in 177 participants, comprising 91 migraine patients (MO) during their interictal period and 86 healthy volunteers (HV). Eleven neurophysiological variables were analyzed, and Principal Component Analysis (PCA) and Forward Feature Selection (FFS) techniques were independently employed to identify relevant variables, refine the feature space, and enhance model interpretability. The ANNs were then trained independently with the features derived from the PCA and FFS to delineate the relationship between electrophysiological inputs and the diagnostic outcome. Results Both models demonstrated robust performance, achieving over 68% in all the performance metrics (accuracy, sensitivity, specificity, and F1 scores). The classification model trained with FFS-derived features performed better than the model trained with PCA results in distinguishing patients with MO from HV. The model trained with FFS-derived features achieved a median accuracy of 72.8% and an area under the curve (AUC) of 0.79, while the model trained with PCA results showed a median accuracy of 68.9% and an AUC of 0.75. Conclusion Our findings suggest that ANNs trained with SSEP-derived variables hold promise as a noninvasive tool for migraine classification, offering potential for clinical application and deeper insights into migraine diagnostics. |
| format | Article |
| id | doaj-art-ae83487c9a57417494c9d48639dfde03 |
| institution | OA Journals |
| issn | 1129-2377 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | BMC |
| record_format | Article |
| series | The Journal of Headache and Pain |
| spelling | doaj-art-ae83487c9a57417494c9d48639dfde032025-08-20T02:25:41ZengBMCThe Journal of Headache and Pain1129-23772025-04-0126111410.1186/s10194-025-01989-2Artificial neural networks applied to somatosensory evoked potentials for migraine classificationGabriele Sebastianelli0Daniele Secci1Francesco Casillo2Chiara Abagnale3Cherubino Di Lorenzo4Mariano Serrao5Shuu-Jiun Wang6Fu-Jung Hsiao7Gianluca Coppola8Department of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTDepartment of Engineering and Architecture, University of ParmaDepartment of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTDepartment of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTDepartment of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTDepartment of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTBrain Research Center, National Yang Ming Chiao Tung UniversityBrain Research Center, National Yang Ming Chiao Tung UniversityDepartment of Medico-Surgical Sciences and Biotechnologies, Sapienza University of Rome Polo Pontino ICOTAbstract Background Finding a biomarker to diagnose migraine remains a significant challenge in the headache field. Migraine patients exhibit dynamic and recurrent alterations in the brainstem-thalamo-cortical loop, including reduced thalamocortical activity and abnormal habituation during the interictal phase. Although these insights into migraine pathophysiology have been valuable, they are not currently used in clinical practice. This study aims to evaluate the potential of Artificial Neural Networks (ANNs) in distinguishing migraine patients from healthy individuals using neurophysiological recordings. Methods We recorded Somatosensory Evoked Potentials (SSEPs) to gather electrophysiological data from low- and high-frequency signal bands in 177 participants, comprising 91 migraine patients (MO) during their interictal period and 86 healthy volunteers (HV). Eleven neurophysiological variables were analyzed, and Principal Component Analysis (PCA) and Forward Feature Selection (FFS) techniques were independently employed to identify relevant variables, refine the feature space, and enhance model interpretability. The ANNs were then trained independently with the features derived from the PCA and FFS to delineate the relationship between electrophysiological inputs and the diagnostic outcome. Results Both models demonstrated robust performance, achieving over 68% in all the performance metrics (accuracy, sensitivity, specificity, and F1 scores). The classification model trained with FFS-derived features performed better than the model trained with PCA results in distinguishing patients with MO from HV. The model trained with FFS-derived features achieved a median accuracy of 72.8% and an area under the curve (AUC) of 0.79, while the model trained with PCA results showed a median accuracy of 68.9% and an AUC of 0.75. Conclusion Our findings suggest that ANNs trained with SSEP-derived variables hold promise as a noninvasive tool for migraine classification, offering potential for clinical application and deeper insights into migraine diagnostics.https://doi.org/10.1186/s10194-025-01989-2Artificial intelligenceNeurophysiologyEvoked potentialsHabituationSensitizationThalamus |
| spellingShingle | Gabriele Sebastianelli Daniele Secci Francesco Casillo Chiara Abagnale Cherubino Di Lorenzo Mariano Serrao Shuu-Jiun Wang Fu-Jung Hsiao Gianluca Coppola Artificial neural networks applied to somatosensory evoked potentials for migraine classification The Journal of Headache and Pain Artificial intelligence Neurophysiology Evoked potentials Habituation Sensitization Thalamus |
| title | Artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| title_full | Artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| title_fullStr | Artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| title_full_unstemmed | Artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| title_short | Artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| title_sort | artificial neural networks applied to somatosensory evoked potentials for migraine classification |
| topic | Artificial intelligence Neurophysiology Evoked potentials Habituation Sensitization Thalamus |
| url | https://doi.org/10.1186/s10194-025-01989-2 |
| work_keys_str_mv | AT gabrielesebastianelli artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT danielesecci artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT francescocasillo artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT chiaraabagnale artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT cherubinodilorenzo artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT marianoserrao artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT shuujiunwang artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT fujunghsiao artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification AT gianlucacoppola artificialneuralnetworksappliedtosomatosensoryevokedpotentialsformigraineclassification |