Kişisel Bilgiler ve Günlük Aktiviteler Gibi Tetikleyicilerin Migren Atağı Üzerindeki Etkilerinin Makine ve Derin Öğrenme Yaklaşımları ile Analizi

Yıl 2021, Sayı: 28, 1233 - 1236, 30.11.2021

Çağlar Gürkan Sude Kozalıoğlu Merih Palandöken

https://doi.org/10.31590/ejosat.1014212

Öz

Dünyadaki en yaygın üçüncü hastalık olan migren, hastaların yaşam kalitesini olumsuz etkilemektedir. Kişisel bilgilerin ve genetik özelliklerin migren hastalığı üzerindeki etkisi bilinmektedir. Yapay zekanın kullanımıyla sağlık alanındaki verilerin analiz edilmesi oldukça önemlidir. Bu çalışmada kullanılan veri seti 'migren atağı olan' ve 'migren atağı olmayan' günlerde elde edilen ve çeşitli migren tetikleyicilerini içeren 4579 örnekten oluşmaktadır. Bu tetikleyicilerin etkisi ile gün içinde migren atağı olan veya olmayan hastalar makine öğrenmesi ve derin öğrenme yöntemleri kullanılarak analiz edilmiştir. Tüm analizler içerisinde, en yüksek kestirimci performans çok katmanlı algılayıcı algoritması tarafından %99.7 doğruluk oranı ve %97.7 F1-skoru ile elde edilmiştir.

Anahtar Kelimeler

Migren atakları, Migren tetikleyicileri, Yapay zeka, Makine öğrenmesi, Derin öğrenme

Teşekkür

Park JW, Chu MK, Kim JM, Park SG ve Cho SJ’ye yapmış oldukları anket çalışması sonuçlarını halka açık olarak paylaştıklarından dolayı bilime yapmış oldukları katkı için teşekkür ederiz.

Analysis of the Effects of Triggers Like Personal Information and Daily Activities on Migraine Attack with Machine and Deep Learning Approaches

Öz

Migraine the third most common disease in the world, is negatively affected the quality of life of patients. The effect of personal information and genetic characteristics on migraine disease is known. It is quite important to analysed data in the field of health with the use of artificial intelligence. The data set used in this study consists of 4579 samples obtained on 'with a migraine attack' and 'without a migraine attack' days and containing several migraine triggers. With the effect of these triggers, the patients with or without migraine attacks during the day were analyzed using machine learning and deep learning methods. Among all analyses, the highest predictive performance has been obtained by the multilayer perceptron algorithm with an accuracy of 99.7% and an F1-score of 97.7%.

Anahtar Kelimeler

Migraine attacks, Migraine triggers, Artificial intelligence, Machine learning, Deep learning

Kaynakça

• Migraineresearchfoundation.org. (2015). Migraine Research Foundation -- About Migraine. Retrieved February 27, 2021, from MRF web site website: https://migraineresearchfoundation.org/about-migraine/migraine-facts/
• Mayo Clinic. (2020). Trichinosis - Symptoms and causes - Mayo Clinic. Retrieved February 27, 2021, from mayoclinic.org website: https://www.mayoclinic.org/diseases-conditions/migraine-headache/symptoms-causes/syc-20360201
• Berengueres, J., & Cadiou, F. (2016). Migraine factors as reported by smartphone users. Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, 2016-Octob, 271–274. https://doi.org/10.1109/EMBC.2016.7590692
• Liu, C., Holroyd, K. A., Zhu, Q., Shen, K., & Zhou, W. (2010). Design and implementation of a behavioral migraine management iPhone app for adolescents with migraine. 2010 IEEE International Symposium on “A World of Wireless, Mobile and Multimedia Networks”, WoWMoM 2010 - Digital Proceedings. https://doi.org/10.1109/WOWMOM.2010.5534985
• Garcia-Chimeno, Y., Garcia-Zapirain, B., Gomez-Beldarrain, M., Fernandez-Ruanova, B., & Garcia-Monco, J. C. (2017). Automatic migraine classification via feature selection committee and machine learning techniques over imaging and questionnaire data. BMC Medical Informatics and Decision Making, 17(1). https://doi.org/10.1186/s12911-017-0434-4
• Park, J. W., Chu, M. K., Kim, J. M., Park, S. G., & Cho, S. J. (2016). Analysis of trigger factors in episodic migraineurs using a smartphone headache diary applications. PLoS ONE, 11(2). https://doi.org/10.1371/journal.pone.0149577
• Han, J., Kamber, M., & Pei, J. (2012). Data Mining: Concepts and Techniques. In Data Mining: Concepts and Techniques. https://doi.org/10.1016/C2009-0-61819-5
• Cortes, C., & Vapnik, V. (1995). Support-Vector Networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1023/A:1022627411411 Safavian, S. R., & Landgrebe, D. (1991). A Survey of Decision Tree Classifier Methodology. IEEE Transactions on Systems, Man and Cybernetics, 21(3), 660–674. https://doi.org/10.1109/21.97458
• Ruppert, D. (2004). The Elements of Statistical Learning: Data Mining, Inference, and Prediction. Journal of the American Statistical Association, 99(466), 567–567. https://doi.org/10.1198/jasa.2004.s339
• Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
• Mayr, A., Binder, H., Gefeller, O., & Schmid, M. (2014). The evolution of boosting algorithms: From machine learning to statistical modelling. Methods of Information in Medicine, 53(6), 419–427. https://doi.org/10.3414/ME13-01-0122