Balistokardiyografi sinyalleri ile derin öğrenme tabanlı hipertansiyon tespiti

Öz

Kan basıncı, damarlardaki kanın damar duvarlarına uyguladığı basınçtır. Bu basınç değerinin normal kabul edilen seviyelerin üzerinde seyir etmesi yüksek tansiyon (YT) veya hipertansiyon (HPT) olarak bilinir. Hayat kalitesini negatif yönde etkileyen, çoğu zaman organlarda çeşitli tahribatlara sebep olan ve ölümlere yol açabilen bu sağlık probleminin teşhisi oldukça önemlidir. Bu çalışmada, balistokardiyografi (BKG) sinyalleri kullanılarak HPT'nin otomatik teşhisine yönelik bir yöntem önerilmiştir. Bunun için BKG sinyalleri, sürekli dalgacık dönüşümü filtre bankası (SDDFB) yöntemi kullanılarak zaman-frekans domenine taşınmıştır. Bu işlemler yapılırken kullanılan dönüşüm yönteminde bazı parametre ayarları gerçekleştirilerek dönüşümün kalitesi arttırılmıştır. Daha sonra elde edilen görüntüler ResNet18, ResNet50, VGG16 ve AlexNet evrişimsel sinir ağlarıyla sınıflandırılmış ve elde edilen sonuçlar karşılaştırılmıştır. Önerilen yöntem ile ResNet18, ResNet50, VGG16 ve AlexNet mimarileri için sırasıyla %98,92, %99,34 ve %99,22 ve %98,07 sınıflandırma doğruluğu elde etmiştir. Elde edilen bu yüksek sınıflandırma sonuçları önerilen yöntemin hipertansiyon teşhisi için kullanılabileceğini ispatlar niteliktedir.

Anahtar Kelimeler

• Hipertansiyon
• BKG sinyali
• Derin Öğrenme
• Sürekli Dalgacık Dönüşümü Filtre Bankası

Deep learning based hypertension detection with ballistocardiography signals

Abstract

Blood pressure is the pressure exerted by the blood in the vessels against the vessel walls. If this pressure value is above normal levels, it is known as high blood pressure (HBP) or hypertension (HPT). The diagnosis of this health problem, which negatively affects the quality of life, often causes various damage to organs and can lead to death, is very important. In this study, a method for automatic diagnosis of HPT using ballistocardiography (BCG) signals is proposed. For this, BCG signals are transferred to the time-frequency domain using the continuous wavelet transform filter bank (CWTFB) method. The quality of the conversion has been increased by making some parameter settings in the conversion method used while performing these operations. Then, the obtained images were classified with ResNet18, ResNet50, VGG16 and AlexNet convolutional neural networks and the obtained results were compared. With the proposed method, classification accuracy of 98.92%, 99.34%, 99.22% and 98.07% was obtained for ResNet18, ResNet50, VGG16 and AlexNet architectures, respectively. These high classification results obtained prove that the proposed method can be used for the diagnosis of hypertension.

Keywords

• Hypertension
• BCG signals
• Deep learning
• Continuous wavelet transform filter bank

Kaynakça

1. A. N. Desai, High Blood Pressure. JAMA. 324(12):1254–1255, 2020. https://doi.org/10.1001/jam a.2020.11289
2. M. Vaduganathan, G. Mensah and J. Turco, The Global Burden of Cardiovascular Diseases and Risk. J Am Coll Cardiol. 80(25), 2361–2371, 2022. https://doi.org/10.1 016/j.jacc.2022.11.005
3. B. Zhou, R. M. Carrillo-Larco, G. Danaei, L. M. Riley, C. J. Paciorek, G. A. Stevens and J. Breckenkamp, Worldwide trends in hypertension prevalence and progress in treatment and control from 1990 to 2019: a pooled analysis of 1201 population-representative studies with 104 million participants. The Lancet, 398(10304), 957-980, 2021. https://doi.org/10.1016/S 0140-6736(21)01330-1
4. R. M. Carey and P. K. Whelton, 2017 ACC/AHA Hypertension Guideline Writing Committee*. Prevention, detection, evaluation, and management of high blood pressure in adults: synopsis of the 2017 American College of Cardiology/American Heart Association Hypertension Guideline. Annals of internal medicine, 168(5), 351-358,2018. https://doi.org/10.73 26/M17-3203
5. M. D. Zink, C. Brüser, B. O Stüben, A. Napp, R. Stöhr, S. Leonhardt and J. Schiefer, Unobtrusive nocturnal heartbeat monitoring by a ballistocardiographic sensor in patients with sleep disordered breathing. Scientific reports, 7(1), 1-13, 2017. https://doi.org/10.1038/s415 98-017-13138-0
6. O. T. Inan, P. F. Migeotte, K. S. Park , M. Etemadi, K. Tavakolian, R. Casanella, and M. Di Rienzo, Ballistocardiography and seismocardiography: A review of recent advances. IEEE journal of biomedical and health informatics, 19(4), 1414-1427,2014. https:// doi.org/10.1109/JBHI.2014.2361732.
7. M. D. Zink, C. Brüser, P. Winnersbach, A. Napp, S. Leonhardt, N. Marx and K. Mischke, Heartbeat cycle length detection by a ballistocardiographic sensor in atrial fibrillation and sinus rhythm. BioMed research international,2015.https://doi.org/10.1155/2015/840356
8. K. S. Parmar, A. Kumar and U. Kalita, ECG signal based automated hypertension detection using fourier decomposition method and cosine modulated filter banks. Biomedical Signal Processing and Control, 76, 103629, 2022. https://doi.org/10.1016/j.bspc.2022. 103 629

9. A. L. Goldberger, L. A. Amaral, L. Glass, J. M. Hausdorff, P. C. Ivanov, R. G. Mark and H. E. Stanley, PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101(23), 215-220, 2000. https://doi.org/10.1161/01.CIR.101.23.e215
10. G. B. Moody, R. G. Mark and A. L. Goldberger, PhysioNet: Physiologic signals, time series and related open source software for basic, clinical, and applied research. In 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society 8327-8330,2011. https://doi.org/10.1109/IEMBS. 2011. 6092053
11. D. C. K. Soh, E. Y. K. Ng, V. Jahmunah, , S. L. Oh, San R. Tan and U. R. Acharya, Automated diagnostic tool for hypertension using convolutional neural network. Computers in Biology and Medicine, 126, 103999,2020. https://doi.org/10.1016/j.compbiomed. 2 020.103999 .
12. J. S. Rajput, M. Sharma and U. R. Acharya. Hypertension diagnosis index for discrimination of high-risk hypertension ECG signals using optimal orthogonal wavelet filter bank. International journal of environmental research and public health, 16(21), 4068, 2019. https://doi.org/10.3390/ijerph16214068.
13. A. Ari, F. Ayaz ve D. Hanbay. EMG sinyallerinin kısa zamanlı fourier dönüşüm özellikleri kullanılarak yapay sinir ağları ile sınıflandırılması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(2), 443-451, 2019. https://doi.org/10.35234/fumbd.545161
14. Arı, A. (2020). Analysis of EEG signal for seizure detection based on WPT. Electronics Letters, 56(25), 1381-1383. https://doi.org/10.1049/el.2020.2701
15. M. Turkoglu, M. Aslan, A. Ari , Z. M. Alçin & D. Hanbay. A multi-division convolutional neural network-based plant identification system. PeerJ Computer Science, 7, e572, 2021. https://doi.org/10.7717/peerj-cs. 572
16. Donuk, K., Ari, A., & Hanbay, D. A CNN based real-time eye tracker for web mining applications. Multimedia Tools and Applications, 81(27), 39103-39120, 2022. https://doi.org/10.1007/s11042-022-1308 5-7
17. A. Ari, Multipath feature fusion for hyperspectral image classification based on hybrid 3D/2D CNN and squeeze-excitation network. Earth Science Informatics, 1-17,2023, https://doi.org/10.55525/tjst.1261887 .
18. Y. Song , H. Ni, X. Zhou, W. Zhao and T. Wang, Extracting features for cardiovascular disease classification based on ballistocardiography. In 2015 IEEE 12th Intl Conf on Ubiquitous Intelligence and Computing and 2015 IEEE 12th Intl Conf on Autonomic and Trusted Computing and 2015 IEEE 15th Intl Conf on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom), pp. 1230-1235, Beijing, China, August 2015.
19. F. Liu, X. Zhou, , Z. Wang, J. Cao, H. Wang and Y. Zhang, Unobtrusive mattress-based identification of hypertension by integrating classification and association rule mining. Sensors, 19(7), 1489, 2019. https://doi.org/10.3390/s19071489
20. J. S. Rajput, M. Sharma , T. S. Kumar and U. R. Acharya. Automated detection of hypertension using continuous wavelet transform and a deep neural network with Ballistocardiography signals. International Journal of Environmental Research and Public Health, 19(7), 4014, 2022. https://doi.org/10.3390/ijerph19074014.
21. K. Gupta, V. Bajaj and I. A Ansari, A support system for automatic classification of hypertension using BCG signals. Expert Systems with Applications, 214, 119058, 2023. https://doi.org/10.1016/j.eswa.2022.119058.
22. K. Gupta, V. Bajaj , I. A. Ansari and U. R. Acharya, Hyp-Net: Automated detection of hypertension using deep convolutional neural network and Gabor transform techniques with ballistocardiogram signals. Biocybernetics and Biomedical Engineering, 42(3), 784-796,2022. https://doi.org/10.1016/ j.bbe.2022.06.0 01.
23. W. Seok, K. J. Lee, D. Cho, J. Roh and S. Kim, Blood pressure monitoring system using a two-channel ballistocardiogram and convolutional neural networks. Sensors, 21(7), 2303, 2021. https://doi.org/10.3390/s21 072303
24. J. S. Rajput, M. Sharma, D. Kumbhani and U. R. Acharya, Automated detection of hypertension using wavelet transform and nonlinear techniques with ballistocardiogram signals. Informatics in Medicine Unlocked, 26, 100736, 2021. https://doi.org/10.3390/ s21072303.
25. S. T. Ozcelik, H. Uyanık, , E. Deniz and A. Sengur, Automated Hypertension Detection Using ConvMixer and Spectrogram Techniques with Ballistocardiograph Signals. Diagnostics, 13(2), 182, 2023. https://doi.org /10.3390/diagnostics13020182.
26. I. S. Chang, J. Boger, S. Mak, S. L. Grace, A. Arcelus, C. Chessex and A. Mihailidis, Load Distribution Analysis for Weight and Ballistocardiogram Measurements of Heart Failure Patients using a Bed Scale. In 2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC) pp. 7369-7372, Mexico, November 2021.
27. M. Köseoğlu and H. Uyanık, Effect of Spectrogram Parameters and Noise Types on The Performance of Spectro-temporal Peaks Based Audio Search Method. Gazi University Journal of Science, 2022. https:// doi.org/10.35378/gujs.1000594
28. M. Köseoğlu, & H. Uyanık, The Effect of Different Noise Levels on The Performance of The Audio Search Algorithm. In 2020 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA) pp. 1-7, Ankara, Turkey, June 2020.
29. H. Uyanık, & M. Köseoğlu, Performance Evaluation of Different Window Functions for Audio Fingerprint Based Audio Search Algorithm. In 2020 4th International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT), pp. 1-4, Ankara, Turkey, October 2020.
30. D. Şengür, & S. Siuly, Efficient approach for EEG‐based emotion recognition. Electronics Letters, 56(25), 1361-1364, 2020. https://doi.org/10.1049/el.2020.2685.
31. H. Uyanık, S. T. A. Ozcelik, Z. B. Duranay , A. Sengur, & U. R. Acharya , Use of Differential Entropy for Automated Emotion Recognition in a Virtual Reality Environment with EEG Signals. Diagnostics, 12(10), 2508,2022.https://doi.org/10.3390/diagnostics12102508.
32. Ari, B., Sobahi, N., Alçin, Ö. F., Sengur, A., & Acharya, U. R. (2022). Accurate detection of autism using Douglas-Peucker algorithm, sparse coding based feature mapping and convolutional neural network techniques with EEG signals. Computers in Biology and Medicine, 143, 105311 https://doi.org/10.1016/j.compbiomed.202 2.105311 .
33. Sobahi, N., Ari, B., Cakar, H., Alcin, O. F., & Sengur, A. (2022). A new signal to image mapping procedure and convolutional neural networks for efficient schizophrenia detection in eeg recordings. IEEE Sensors Journal, 22(8), 7913-7919 https://doi.org/10.1109/JSEN .2022.3151465 .
34. Ari, B., Siddique, K., Alçin, Ö. F., Aslan, M., Şengür, A., & Mehmood, R. M. (2022). Wavelet ELM-AE Based Data Augmentation and Deep Learning for Efficient Emotion Recognition Using EEG Recordings. IEEE Access, 10, 72171-72181 https://doi.org/10.1109 /ACCESS.2022.3181887 .
35. https://www.mathworks.com/help/matlab/ref/double.normalize.html#mw_dcfb89d2-e230-4be0-bb16-d672f91b8e91
36. J. M. Lilly, & S. C. Olhede. Higher-order properties of analytic wavelets. IEEE Transactions on Signal Processing, 57(1), 146-160, 2008. https://doi.org/10.110 9/TSP.2008.2007607.
37. K. He, X. Zhang, S. Ren and J. Sun, Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770-778,Las Vegas, USA, June 2016.
38. K. He, X. Zhang, S. Ren and J. Sun, Identity mappings in deep residual networks. In European conference on computer vision, pp. 630-645, Amsterdam,Netherlands, October, 2016.
39. K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014. http s://doi.org/10.48550/arXiv.1409.1556