EHG sinyallerinden Erken Doğum Tespiti

Yıl 2021, Sayı: 28, 1283 - 1287, 30.11.2021

Ahmet Sağlam , Ümit Şentürk , İbrahim Yücedağ

https://doi.org/10.31590/ejosat.1014179

Öz

Erken doğum dünya genelinde büyük problemlerden biridir. Geçmişten günümüze kadar erken doğumu tespit etmek amacıyla farklı yöntemler araştırılmış ve kullanılmıştır. En yaygın kullanılanları ise; Tokodinamometre cihazı, Transvajinal Serviks Uzunluğu, Bishop Skoru ve ElectroHysteroGram (EHG) sinyalidir. Yapılan araştırmalar, EHG sinyalleri kullanılarak Erken doğum riskinin tahmin edilmesinde yaygın olarak kullanıldığı gözlenmiştir. Çalışmalarda, EHG sinyallerinden öznitelik çıkartımı yapılıp, çeşitli regresyon algoritmaları ile Erken doğum riski tahmin edilmiştir. Bu çalışmada, EHG sinyalleri ile erken doğum tespitinde kullanılan yöntemlerde SMOTE algoritması incelenmiş ve kıyaslaması yapılmıştır. Sonuç olarak tüm yöntemlerde SMOTE algoritmasının sonuca ulaşmada etkili olduğu görülmüştür. Bu çalışmada, en iyi sonuç CNN algoritması ile elde edilmiştir

Anahtar Kelimeler

EHG, erken doğum, makine öğrenmesi, derin sinir ağları, CNN

Premature Birth Detection from EHG signals

Öz

Premature birth is one of the major problems worldwide. Different methods have been researched and used to detect preterm birth from past to present. The most commonly used ones are; The tocodynamometer device is Transvaginal Cervix Length, Bishop Score and ElectroHysteroGram (EHG) signal. Studies have shown that it is widely used in estimating the risk of preterm birth using EHG signals. In the studies, feature extraction was made from EHG signals and preterm birth risk was estimated with various regression algorithms. In this study, the SMOTE algorithm in the methods used in the detection of preterm birth with EHG signals was examined and compared. As a result, it has been seen that the SMOTE algorithm is effective in reaching the result in all methods. In this study, the best result was obtained with the CNN algorithm

Anahtar Kelimeler

EHG, preterm birth, machine learning, deep neural networks, CNN

Kaynakça

• Acharya, U. R., Sudarshan, V. K., Rong, S. Q., Tan, Z., Lim, C. M., Koh, J. E., ... & Bhandary, S. V. (2017). Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals. Computers in biology and medicine, 85.
• Ahmed, M. U., Chanwimalueang, T., Thayyil, S., & Mandic, D. P. (2017). A multi variate multiscale fuzzy entropy algorithm with application to uterine EMG complexity analysis, Entropy, 19(1), doi: 10.3390/e19010002.
• Alamedine, D. (2005). Election of EHG parameter characteristics for the classification of uterine contractions, PHD thesis, Université Libanaise.
• Alexandersson, Á. (2015). Conceiving, compiling, publishing and exploiting the ‘Icelandic 16-electrode EHG database’, PHD Thesis. Háskólinn í Reykjavík.
• Alyanak, Ç. M. (2020). Türkiye’de her 10 bebekten biri hayata erken başlıyor, https://www.aa.com.tr/tr/saglik/prof-dr-koc-turkiyede-her-10-bebekten-biri-hayata-erken-basliyor /1306225 (erişim Kas. 17, 2020).
• Callahan T. & Caughey, A. B., (2013). Obstetrics & Gynecology Sixth Edition, Lippincott Williams & Wilkins: U.S.A.
• Chen L. & Hao, Y. (2017). Feature Extraction and Classification of EHG between Pregnancy and Labour Group Using Hilbert-Huang Transform and Extreme Learning Machine, Comput. Math. Methods Med., doi: 10.1155/2017/7949507.
• Degbedzui, D. K. & Yüksel, M. E. (2020). Accurate diagnosis of term–preterm births by spectral analysis of electrohysterography signals, Comput. Biol. Med., 119, doi: 10.1016/j.compbiomed.2020.103677.
• Euliano, T. Y., Nguyen, M. T., Darmanjian, S., McGorray, S. P., Euliano, N., Onkala, A., & Gregg, A. R. (2013). Monitoring uterine activity during labor: a comparison of 3 methods. American journal of obstetrics and gynecology, 208(1), doi: 10.1016/j.ajog.2012.10.873.
• Fele-Žorž, G., Kavšek, G., Novak-Antolič, Ž., & Jager, F., (2008). A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups, Med. Biol. Eng. Comput., 46 (9), doi: 10.1007/s11517-008-0350-y.
• Greenough, A. (2013). Long-term respiratory consequences of premature birth at less than 32 weeks of gestation, Early Hum. Dev., 89, doi: 10.1016/j.earlhumdev.2013.07.004.
• Idowu, I. O. (2017). Classification Techniques Using EHG Signals for Detecting Preterm Births, PHD thesis, Liverpool John Moores University.
• Jager, F., Libenšek, S., & Geršak, K., (2018). Characterization and automatic classification of preterm and term uterine records, PLoS One, 13 (8), doi: 10.1371/journal.pone.0202125.
• Kenny L. C. & Myers, J. E. (2020). OBSTETRICS | 20th EDITION by Ten Teachers, Lippincott Williams & Wilkins: U.S.A.
• Khalil M. & Duchêne, J. (2000). Uterine EMG analysis: A dynamic approach for change detection and classification, IEEE Trans. Biomed. Eng., 47(6), doi: 10.1109/10.844224.
• Léman, H., Marque, C. & Gondry, J. (1999). Use of the electrohysterogram signal for characterization of contractions during pregnancy, IEEE Trans. Biomed. Eng., 46(10), doi: 10.1109/10.790499.
• Lucovnik, M., Chambliss, L. R., Blumrick, R., Balducci, J., Gersak, K., & Garfield, R. E. (2016). Effect of obesity on preterm delivery prediction by transabdominal recording of uterine electromyography, Taiwan. J. Obstet. Gynecol., 55 (5), doi: 10.1016/j.tjog.2015.05.005.
• Maner, W. L., Garfield, R. E., Maul, H., Olson, G., & Saade, G. (2003). Predicting term and preterm delivery with transabdominal uterine electromyography, Obstet. Gynecol., 101(6), doi: 10.1016/S0029-7844(03)00341-7.
• Muszynski, L.C. (2019). Évaluation de l’électrohystérogramme pour la surveillance et le diagnostic des femmes à risqué d’accouchement premature, PHD thesis, Université de Technologie de Compiègne.
• Verdenik, I., Pajntar, M., & Leskošek, B. (2001). Uterine electrical activity as predictor of preterm birth in women with preterm contractions, Eur. J. Obstet. Gynecol. Reprod. Biol., 95(2), doi: 10.1016/S0301-2115(00)00418-8.
• Ye-Lin, Y., Garcia-Casado, J., Prats-Boluda, G., Alberola-Rubio, J., & Perales, A. (2014). Automatic identification of motion artifacts in EHG recording for robust analysis of uterine contractions, Comput. Math. Methods Med., doi: 10.1155/2014/470786.
• Yochum, M., Laforêt, J., & Marque, C., (2016). An electro-mechanical multiscale model of uterine pregnancy contraction, Comput. Biol. Med., 77, doi: 10.1016/j.compbiomed.2016.08.001