Journals / Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi / 2026 / Cilt: 26 Sayı: 1

Determination of Effective Flash Stimulation Frequency and EEG Channels with Machine Learning Algorithms to Detect Migraine in Children

Çocuklarda Migren Tespiti İçin Işıklı Uyarım Frekansı ve EEG Kanallarının Belirlenmesi: Makine Öğrenmesi Algoritmaları ile Bir Yaklaşım

Ugur Fidan(AFYON KOCATEPE ÜNİVERSİTESİ)0000-0003-0356-017X
Emin Ibılı(Afyonkarahisar Sağlık Bilimleri Üniversitesi)0000-0002-6186-3710
Dilek Çavuşoğlu(Afyonkarahisar Sağlık Bilimleri Üniversitesi)0000-0003-4924-5300
Neşe Özkan Yılmaz(AFYON KOCATEPE ÜNİVERSİTESİ, MÜHENDİSLİK FAKÜLTESİ)0000-0003-4411-4838
Nurullah Okumuş(Afyonkarahisar Sağlık Bilimleri Üniversitesi)0000-0001-6082-0818
Pages
223–237
Publication Date
2026-01-19
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This research underscores the potential of EEG-based artificial intelligence methods for early diagnosis and monitoring of pediatric migraine, offering a novel perspective to the literature.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:This study aims to evaluate the usability of electroencephalography (EEG) data obtained under photic stimulation in diagnosing pediatric migraine.
📊
Key Findings & Data:EEG data from 20 children diagnosed with migraine and 18 healthy controls aged 6–18 years were analyzed.
💡
Conclusion & Impact:This research underscores the potential of EEG-based artificial intelligence methods for early diagnosis and monitoring of pediatric migraine, offering a novel perspective to the literature.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Migren · Çocuk · EEG

Abstract

This study aims to evaluate the usability of electroencephalography (EEG) data obtained under photic stimulation in diagnosing pediatric migraine. EEG data from 20 children diagnosed with migraine and 18 healthy controls aged 6–18 years were analyzed. EEG recordings were acquired using the OpenBCI Cyton+Daisy system, and photic stimulation at increasing frequencies between 2–16 Hz was applied. Data were analyzed using the wavelet transform method, and significant arousal patterns were detected in FP1, FP2, T5, and T6 channels. Classification with Support Vector Machine (SVM) and Multilayer Artificial Neural Network (ANN) algorithms revealed that the SVM method achieved the highest accuracy (76.35%) at 6 Hz, while the ANN method achieved 79.05% accuracy at 12 Hz. The findings suggest that EEG data can reveal distinct patterns at different frequencies and channels in pediatric migraine patients. The results align partially with adult migraine studies, yet the prominent response at 6 Hz and 12 Hz in children highlights the study’s unique contribution. This research underscores the potential of EEG-based artificial intelligence methods for early diagnosis and monitoring of pediatric migraine, offering a novel perspective to the literature.

Özet

Bu çalışma, çocukluk çağı migren hastalarında elektroensefalografi (EEG) verilerinin ışıklı stimülasyon altında analiz edilerek migren tanısında kullanılabilirliğini değerlendirmeyi amaçlamaktadır. Çalışmada, 6–18 yaş aralığında migren tanısı almış 20 çocuk ve 18 sağlıklı kontrol olgusunun EEG verileri incelenmiştir. EEG kayıtları OpenBCI Cyton+Daisy cihazı kullanılarak elde edilmiş ve 2–16 Hz arasında artan frekanslarda ışıklı stimülasyon uygulanmıştır. Veriler dalgacık dönüşümü yöntemiyle analiz edilmiş, FP1, FP2, T5 ve T6 kanallarında anlamlı uyarılma paternleri tespit edilmiştir. Destek Vektör Makineleri (SVM) ve Çok Katmanlı Yapay Sinir Ağı (ANN) algoritmaları kullanılarak yapılan sınıflandırmalarda, SVM yöntemi 6 Hz frekansında %76,35 doğruluk oranı ile en iyi sonucu verirken, ANN yöntemi 12 Hz frekansında %79,05 doğruluk sağlamıştır. Bulgular, çocukluk çağı migren hastalarında EEG verilerinin farklı frekans ve kanallarda anlamlı paternler oluşturabileceğini göstermiştir. Ayrıca, elde edilen sonuçlar, yetişkin migren çalışmalarındaki bulgularla kısmen uyum göstermekte, ancak çocuk hastalarda 6 Hz ve 12 Hz frekanslarının öne çıkması çalışmanın özgün katkısı olarak değerlendirilmektedir. Bu çalışma, çocukluk çağı migreninin erken tanı ve izlenmesinde EEG tabanlı yapay zeka yöntemlerinin potansiyelini vurgulamakta ve literatüre yeni bir perspektif sunmaktadır.

🔖

Cite This Article

İbili, A. B., Fidan, U., Ibılı, E., Çavuşoğlu, D., Yılmaz, N. Ö., Okumuş, N. (2026). Determination of Effective Flash Stimulation Frequency and EEG Channels with Machine Learning Algorithms to Detect Migraine in Children. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, Cilt: 26 Sayı: 1, 223–237. https://doi.org/10.35414/akufemubid.1711013

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (22)

  1. Abdurrahman L, Keane M. 2024. Understanding migraine: Epidemiology, EEG abnormalities, and the potential of neurofeedback training. NeuroRegulation, 11(2):184–190. https://doi.org/10.15540/nr.11.2.184
  2. Ashokan A, Rehman IU, Saadati P. 2025. Migraine classification using machine learning and deep learning in low-resource healthcare settings. EasyChair Preprints, 15776.
  3. Cervantes J, Garcia-Lamont F, Rodríguez-Mazahua L, Lopez A. 2020. A comprehensive survey on support vector machine classification: Applications, challenges, and trends. Neurocomputing, 408:189-215.
  4. Cordes D, Kaleem MF, Yang Z, Zhuang X, Curran T, Sreenivasan KR, et al. 2021. Energy-period profiles of brain networks in group fMRI resting-state data: A comparison of empirical mode decomposition with the short-time
  5. Fourier transform and the discrete wavelet transform. Front Neurosci, 15:663403.
  6. Dyllon S, Xiao P. 2018. Wavelet transform for educational network data traffic analysis. In: Wavelet Theory and Applications, p. 155.
  7. Garcia-Chimeno Y, Garcia-Zapirain B, Gomez-Beldarrain M, Fernandez-Ruanova B, Garcia-Monco JC. 2017. Automatic migraine classification via feature selection committee and machine learning techniques over imaging and questionnaire data. BMC Med Inform Decis Mak, 17(1):1-10.
  8. Gosala B, Kapgate PD, Jain P, Chaurasia RN, Gupta M. 2023. Wavelet transforms for feature engineering in EEG data processing: An application on schizophrenia. Biomed Signal Process Control, 85:104811.
  9. Guarnera A, et al. 2021. Early alterations of cortical thickness and gyrification in migraine without aura: A retrospective MRI study in pediatric patients. J Headache Pain, 22(1):79.
  10. Kamaşak T, Durgut BD, Arslan EA, Şahin S, Dilber B, Kurt T, Cansu A. 2018. The role of electroencephalography in differentiating epileptic and non-epileptic events in adolescents: A three-year experience of a pediatric neurology center. Güncel Pediatri, 16(2):158-164.
  11. Kazemi S, Katibeh P. 2018. Comparison of parametric and non-parametric EEG feature extraction methods in detection of pediatric migraine without aura. J Biomed Phys Eng, 8(3):305–314.
  12. Kilic B. 2021. Evaluation of the Etiology, Clinical Presentation, Findings, and Prophylaxis of Children with Headache. Şişli Etfal Hospital Medical Bulletin, 55(1):128-133.
  13. Klein A, Aeschlimann SA, Zubler F, Scutelnic A, Riederer F, Ertl M, et al. 2024. Alterations of the alpha rhythm in visual snow syndrome: A case-control study. J Headache Pain, 25(1):53.
  14. Niedermeyer E, Lopes da Silva F. 2020. Electroencephalography: Basic principles, clinical applications, and related fields. 7th ed. Philadelphia: Lippincott Williams & Wilkins.
  15. Ouyang CS, Hsiao FJ, Lo MT, et al. 2020. Quantitative electroencephalogram analysis of frontal cortex functional changes in patients with migraine. Kaohsiung J Med Sci, 36(7):543-551.
  16. Petrušić I, et al. 2024. Machine learning classification meets migraine: Recommendations for study evaluation. J Headache Pain, 25:215.
  17. Raghuraman L, Joshi SH. 2024. Application of EEG in the diagnosis and classification of migraine: A scoping review. Cureus, 16(7):e64961.
  18. Reddy A, Reddy A. 2025. Migraine triggers, phases, and classification using machine learning models. Front Neurol, 16:1555215.
  19. Rho YI, Kim JS, Kim DW, Choi SA, Lim BC, Chae JH, et al. 2020. EEG characteristics and diagnostic implications in childhood headache: A multi-center study. Front Neurol, 11:582516. Rocca MA, Messina R, Colombo B, Falini A, Comi G, Filippi M. 2014. Structural brain MRI abnormalities in pediatric patients with migraine. J Neurol, 261(2):350-357.
  20. Sadeghi S, Maleki A. 2018. Recent advances in hybrid brain-computer interface systems: A technological and quantitative review. Basic Clin Neurosci, 9(5):373.
  21. Subasi A, Ahmed A, Aličković E, Hassan AR. 2019. Effect of photic stimulation for migraine detection using random forest and discrete wavelet transform. Biomed Signal Process Control, 49:231-239. Vapnik V. 1995. The nature of statistical learning theory. New York: Springer Verlag.
  22. https://www.tutorialspoint.com/artificial_neural_network/artificial_neural_network_basic_concepts.htm (09.07.2025)