Konferans Bildirisi
BibTex RIS Kaynak Göster

Wavelet Dalgacık Dönüşümü ile Tıkayıcı Uyku Apnesi Tahmini ve Epok Sürelerinin Etkisi

Yıl 2021, Sayı: 26 - Ejosat Özel Sayı 2021 (HORA), 276 - 283, 31.07.2021
https://doi.org/10.31590/ejosat.954003

Öz

Tıkayıcı uyku apnesi halk arasında uykuda nefes durması olarak da bilinen çok ciddi bir halk sağlığı sorunudur. Bu sağlık sorununun tespit edilmesi ciddi laboratuvar tetkikleri gerektirmektedir. Polisomnografi (PSG) olarak adlandırılan bu tetkik sisteminde hastadan gece boyunca birçok fizyolojik veri toplanarak kaydedilir. Daha sonra bu veriler incelenerek teshis için kullanılır. Bu çalışmada yaşları 34 ile 73 arasında ve vücut kitle endeksleri 24,6 ile 49,3 arasında değişen 24 hastadan elde edilen gerçek veriler kullanılmıştır. Bu hastaların 17’si ciddi, 6’sı orta, 1’i de hafif derecede uyku apnesi teşhisi koyulmuş bireylerdir. 24 hastanın hastanenin uyku servisinde uyuma ve veri toplama için geçirdiği süre ortalama 5 saat 8 dakika 3 saniyedir. Bu çalışmada PSG ile toplanan fizyolojik verilerden olan pressure flow, pressuse snore ve thorax sinyalleri kullanılmıştır. Bu sinyaller önce epoklara ayrılmış, daha sonra ön işlemlerden geçirilmiştir. Farklı epok sürelerinin kullanıldığı çalışmada, her sinyalden wavelet dalgacık dönüşümü yöntemi ile sinyal özellikleri çıkarılarak bir özellikler veri seti oluşturulmuştur. Oluşturulan bu veri seti kullanılarak hastanın uyku sırasında meydana gelecek apnelerin önceden tahmin edilmesi amacıyla bir sistem geliştirilmiştir. Farklı sınıfandırıcıların da kullanıldığı bu sistemde ham sinyallerin bölümlendirilmesinde kullanılan epok sürelerin tahmin başarısına etkisi araştırılmıştır. Epok süresi 30 saniye olarak belirlendiğinde %88 doğruluk oranı elde edilirken, epok süresi 15 saniye olarak belirlendiğinde tahmin doğruluğu %93,3 olarak hesaplanmıştır. Epok süresi 5 saniye olarak belirlendiğinde ise tahmin başarısı %97,2 olarak gerçekleşmiştir. Sonuçlar, epok sürelerinin kısaltılmasının tahmin başarısını artırdığını göstermektedir. Bunun nedeni olarak apne olayının meydana geldiği ana daha yakın bir zaman diliminde elde edilen fizyolojik verilerin, meydana gelecek apneyi daha iyi tanımlamasıdır.

Destekleyen Kurum

Türkiye Bilimsel ve Teknolojik Araştirma Kurumu(TÜBİTAK) ve Selçuk Üniversitesi, Bilimsel Araştırma Projeleri koordinatörlüğü

Proje Numarası

5190006 ve 18101016

Teşekkür

Bu çalışmayı 1505 Üniversite-Sanayi İşbirliği Destek Programı kapsamında 5190006 proje numarası ile destekleyen Türkiye Bilimsel ve Teknolojik Araştirma Kurumu’na (TÜBİTAK) ve 18101016 proje numarası ile destekleyen Selçuk Üniversitesi, Bilimsel Araştırma Projeleri koordinatörlüğüne teşekkürlerimizi sunarız.

Kaynakça

  • American Academy of Sleep Medicine. (2012). The AASM Manual for the Scoring of Sleep and Associated Events The 2007 AASM Scoring Manual vs. the AASM Scoring Manual v2.0.
  • Arı, N., Özen, Ş., & Çolak, Ö. H. (2008). Wavelet Theory. Palme.
  • Bock, J., & Gough, D. A. (1998). Toward prediction of physiological state signals in sleep apnea. IEEE Transactions on Biomedical Engineering, 45(11). https://doi.org/10.1109/10.725330
  • Dagum, P., & Galper, A. (1995). Time series prediction using belief network models. International Journal of Human-Computer Studies, 42(6). https://doi.org/10.1006/ijhc.1995.1027
  • De la Fuente, C., Weinstein, A., Guzman-Venegas, R., Arenas, J., Cartes, J., Soto, M., & Carpes, F. P. (2019). Use of accelerometers for automatic regional chest movement recognition during tidal breathing in healthy subjects. Journal of Electromyography and Kinesiology, 47. https://doi.org/10.1016/j.jelekin.2019.05.016
  • del Campo, F., Hornero, R., Zamarrón, C., Abasolo, D. E., & Álvarez, D. (2006). Oxygen saturation regularity analysis in the diagnosis of obstructive sleep apnea. Artificial Intelligence in Medicine, 37(2). https://doi.org/10.1016/j.artmed.2005.10.005
  • Díaz, J. A., Arancibia, J. M., Bassi, A., & Vivaldi, E. A. (2014). Envelope Analysis of the Airflow Signal To Improve Polysomnographic Assessment of Sleep Disordered Breathing. Sleep, 37(1). https://doi.org/10.5665/sleep.3338
  • Douglas, N. ., Thomas, S., & Jan, M. . (1992). Clinical value of polysomnography. The Lancet, 339(8789). https://doi.org/10.1016/0140-6736(92)91660-Z
  • Huang, W., Guo, B., Shen, Y., & Tang, X. (2017). A novel method to precisely detect apnea and hypopnea events by airflow and oximetry signals. Computers in Biology and Medicine, 88. https://doi.org/10.1016/j.compbiomed.2017.06.015
  • Hyo-Ki Lee, Jeon Lee, Hojoong Kim, & Kyoung-Joung Lee. (2013, July). Automatic snoring detection from nasal pressure data. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). https://doi.org/10.1109/EMBC.2013.6611136
  • Koçyiğit, Y., & Korürek, M. (2005). EMG signal classification using wavelet transform and fuzzy logic classifier. ITU Journal Series D: Engineering, 4(3), 25–31.
  • Miner, N. E. (1998). An Introduction to Wavelet Theory and Analysis. https://doi.org/10.2172/1896
  • Molin, N. L., Molin, C., Dalpatadu, R. J., & Singh, A. K. (2021). Prediction of obstructive sleep apnea using Fast Fourier Transform of overnight breath recordings. Machine Learning with Applications, 4. https://doi.org/10.1016/j.mlwa.2021.100022
  • Özmen, G. (2013). The Evaluation of The Muscle Fatigue in The Cervical Region with Surface Electromyogram Information. The Graduate School of Natural and Applied Science of Selcuk University.
  • Türkoğlu, İ. (2002). An Intelligent pattern recognition for nonstationary signals based on the time-frequency entropies. Fırat University, Institute of Science and Technology.
  • Vetterli, M., & Kovačević, J. (1995). Wavelets and Subband Coding. Prentice Hall PTR.
  • Waxman, J. A., Graupe, D., & Carley, D. W. (2010). Automated Prediction of Apnea and Hypopnea, Using a LAMSTAR Artificial Neural Network. American Journal of Respiratory and Critical Care Medicine, 181(7). https://doi.org/10.1164/rccm.200907-1146OC

Effects of Obstructive Sleep Apnea Prediction and Epoch Duration with Wavelet Wavelet Transform

Yıl 2021, Sayı: 26 - Ejosat Özel Sayı 2021 (HORA), 276 - 283, 31.07.2021
https://doi.org/10.31590/ejosat.954003

Öz

Obstructive sleep apnea is a very serious public health problem, also known as respiratory arrest during sleep. Detection of this health problem requires serious laboratory tests. In this examination system called polysomnography (PSG), many physiological data are collected from the patient during the night and recorded. Then, these data are examined and used for diagnosis. Actual data obtained from 24 patients with body mass indexes between 24.6 and 49.3 and ages between 34 and 73 were used in this study. Seventeen of these patients are individuals who have been diagnosed with severe sleep apnea, 6 of them moderate, and 1 of them mild sleep apnea. The average time 24 patients spend sleeping and data collection in the hospital's sleep service is 5 hours, 8 minutes and 3 seconds. Pressure flow, pressuse snore and thorax signals, which are among the physiological data collected by PSG, were used in this study. These signals were first separated into epocs and then pre-processed. In the study, in which different epoch durations were used, a property data set was created by extracting signal properties from each signal with wavelet wavelet transform method. Using this data set, a system has been developed to predict apneas that will occur during sleep. In this system, in which different classifiers are used, the effect of epoch times used in segmentation of raw signals on prediction success has been investigated. When the epoch duration was determined as 30 seconds, 88% accuracy was obtained, while the prediction accuracy was calculated as 93.3% when the epok duration was determined as 15 seconds. When the epoch duration was determined as 5 seconds, the prediction success was 97.2%. The results show that shortening the epoch times increases prediction success. The reason for this is that the physiological data obtained in a period closer to the moment when the apnea event occurs, better describe the apnea that will occur.

Proje Numarası

5190006 ve 18101016

Kaynakça

  • American Academy of Sleep Medicine. (2012). The AASM Manual for the Scoring of Sleep and Associated Events The 2007 AASM Scoring Manual vs. the AASM Scoring Manual v2.0.
  • Arı, N., Özen, Ş., & Çolak, Ö. H. (2008). Wavelet Theory. Palme.
  • Bock, J., & Gough, D. A. (1998). Toward prediction of physiological state signals in sleep apnea. IEEE Transactions on Biomedical Engineering, 45(11). https://doi.org/10.1109/10.725330
  • Dagum, P., & Galper, A. (1995). Time series prediction using belief network models. International Journal of Human-Computer Studies, 42(6). https://doi.org/10.1006/ijhc.1995.1027
  • De la Fuente, C., Weinstein, A., Guzman-Venegas, R., Arenas, J., Cartes, J., Soto, M., & Carpes, F. P. (2019). Use of accelerometers for automatic regional chest movement recognition during tidal breathing in healthy subjects. Journal of Electromyography and Kinesiology, 47. https://doi.org/10.1016/j.jelekin.2019.05.016
  • del Campo, F., Hornero, R., Zamarrón, C., Abasolo, D. E., & Álvarez, D. (2006). Oxygen saturation regularity analysis in the diagnosis of obstructive sleep apnea. Artificial Intelligence in Medicine, 37(2). https://doi.org/10.1016/j.artmed.2005.10.005
  • Díaz, J. A., Arancibia, J. M., Bassi, A., & Vivaldi, E. A. (2014). Envelope Analysis of the Airflow Signal To Improve Polysomnographic Assessment of Sleep Disordered Breathing. Sleep, 37(1). https://doi.org/10.5665/sleep.3338
  • Douglas, N. ., Thomas, S., & Jan, M. . (1992). Clinical value of polysomnography. The Lancet, 339(8789). https://doi.org/10.1016/0140-6736(92)91660-Z
  • Huang, W., Guo, B., Shen, Y., & Tang, X. (2017). A novel method to precisely detect apnea and hypopnea events by airflow and oximetry signals. Computers in Biology and Medicine, 88. https://doi.org/10.1016/j.compbiomed.2017.06.015
  • Hyo-Ki Lee, Jeon Lee, Hojoong Kim, & Kyoung-Joung Lee. (2013, July). Automatic snoring detection from nasal pressure data. 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). https://doi.org/10.1109/EMBC.2013.6611136
  • Koçyiğit, Y., & Korürek, M. (2005). EMG signal classification using wavelet transform and fuzzy logic classifier. ITU Journal Series D: Engineering, 4(3), 25–31.
  • Miner, N. E. (1998). An Introduction to Wavelet Theory and Analysis. https://doi.org/10.2172/1896
  • Molin, N. L., Molin, C., Dalpatadu, R. J., & Singh, A. K. (2021). Prediction of obstructive sleep apnea using Fast Fourier Transform of overnight breath recordings. Machine Learning with Applications, 4. https://doi.org/10.1016/j.mlwa.2021.100022
  • Özmen, G. (2013). The Evaluation of The Muscle Fatigue in The Cervical Region with Surface Electromyogram Information. The Graduate School of Natural and Applied Science of Selcuk University.
  • Türkoğlu, İ. (2002). An Intelligent pattern recognition for nonstationary signals based on the time-frequency entropies. Fırat University, Institute of Science and Technology.
  • Vetterli, M., & Kovačević, J. (1995). Wavelets and Subband Coding. Prentice Hall PTR.
  • Waxman, J. A., Graupe, D., & Carley, D. W. (2010). Automated Prediction of Apnea and Hypopnea, Using a LAMSTAR Artificial Neural Network. American Journal of Respiratory and Critical Care Medicine, 181(7). https://doi.org/10.1164/rccm.200907-1146OC
Toplam 17 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Mühendislik
Bölüm Makaleler
Yazarlar

Mehmet Balcı 0000-0002-9552-5883

Adem Gölcük 0000-0002-6734-5906

Serkan Küççüktürk Bu kişi benim 0000-0001-8445-666X

Sakir Tasdemır 0000-0002-2433-246X

Hüsamettin Vatansev 0000-0002-0230-3414

Hülya Vatansev 0000-0002-8382-3904

Proje Numarası 5190006 ve 18101016
Yayımlanma Tarihi 31 Temmuz 2021
Yayımlandığı Sayı Yıl 2021 Sayı: 26 - Ejosat Özel Sayı 2021 (HORA)

Kaynak Göster

APA Balcı, M., Gölcük, A., Küççüktürk, S., Tasdemır, S., vd. (2021). Wavelet Dalgacık Dönüşümü ile Tıkayıcı Uyku Apnesi Tahmini ve Epok Sürelerinin Etkisi. Avrupa Bilim Ve Teknoloji Dergisi(26), 276-283. https://doi.org/10.31590/ejosat.954003