Elektrokardiyografi Yardımıyla Hipertansiyonun Otomatik Belirlenmesinde Ampirik Kip Ayrışımının Gürültülü ve Gürültüsüz Sinyaller Üzerindeki Performansının Karşılaştırılması

Öz

Hipertansiyon (HPT), kalpten vücuda taşınan kanın atardamar duvarlarına uyguladığı kuvvetin, bazı hastalıklara sebebiyet verecek kadar yüksek olduğu duruma verilen isimdir. HPT’ye bağlı hastalıklar sonucunda her yıl dünyada birçok insan hayatını kaybetmektedir. Bu sebepten dolayı HPT’nin erken teşhis edilmesi oldukça kritik bir öneme sahiptir. Bu çalışma elektrokardiyogram (EKG) sinyalleri kullanılarak HPT hastalarının otomatik ve en az hata ile tespit edilmesi amacıyla yapılmıştır. Bu çalışmada EKG sinyalleri 4 farklı grupta toplanmıştır. Bu yaklaşımlar sırasıyla, normalize edilmiş gürültülü EKG sinyalleri, normalize edilmiş gürültüsüz EKG sinyalleri, normalize edilmemiş gürültülü EKG sinyalleri ve son olarak normalize edilmemiş gürültüsüz EKG sinyalleridir. Ampirik Kip Ayrışımı metodu vasıtasıyla 5 katmanlı iç mod fonksiyon (İMF) sinyalleri üzerinden elde edilen entropi ölçümleri yardımıyla HPT belirleme performansı analiz edilmiştir. Her bir İMF için elde edilen iki adet öznitelikle başarımlar mukayese edilmiştir. Özetle, 10-kat çapraz doğrulama metodundan yararlanılarak destek vektör makineleri (DVM) algoritmaları ile en yüksek doğruluk değeri %99,99 olarak elde edilmiştir. Elde edilen yüksek performanslardan, HPT hastası kişilerin belirlenmesinde doktorlara yararlı olacağı sonucuna varılabilir.

Anahtar Kelimeler

• Hipertansiyon
• EKG
• Ampirik Kip Ayrışımı
• Destek Vektör Makineleri

Comparison of Performance of Empirical Mode Decomposition on Noisy and Noiseless Signals in Automatic Detection of Hypertension with the Assistance of Electrocardiography

Öz

Hypertension (HPT) is the name given to the condition in which the force exerted by the blood carried from the heart to the body is high enough to cause some diseases. As a result of HPT-related diseases, many people die every year around the world. For this reason, early diagnosis of HPT is of critical importance. This study was conducted to detect HPT patients automatically and with minimum error by using electrocardiogram (ECG) signals. In this study, ECG signals were collected in 4 different groups. These approaches are respectively normalized noisy ECG signals, normalized noiseless ECG signals, unnormalized noisy ECG signals and finally unnormalized noiseless ECG signals. HPT determination performance was analyzed with the help of entropy measurements obtained from 5-layer internal mode function (IMF) signals by means of the Empirical Mode Decomposition method. Performances were compared with two features obtained for each IMF. In summary, the highest accuracy value of 99.99% was obtained with support vector machines (SVM) algorithms by using the 10-fold cross validation method. From the high performances obtained, it can be concluded that it will be useful to doctors in identifying people with HPT.

Anahtar Kelimeler

• Hypertension
• ECG
• Empirical Mode Decomposition
• Support Vector Machines

Kaynakça

1. Tabassum N., Ahmad F., Role of natural herbs in the treatment of hypertension, Pharm. Rev. 5 (9) (2011) 30–40.
2. Sarıışık A.,Oğuz A.,Uzunlulu M., Control of hypertension in Turkey is it improving The Kocaeli 2 study Türkiye’de hipertansiyon kontrolü: Düzelme var mı? Kocaeli 2 çalışması M.D. Department of Internal Medicine, Göztepe Training and Research Hospital, İstanbul
3. Chalmers J. Implementation of guidelines for management of hypertension. Clinical and Experimental Hypertension, 1992, 21:647–657.
4. Drozdz D.,Kawecka-Jaszcz K., Cardiovascular changes during chronic hypertensive states, Pediatr. Nephrol. 29 (9) (2014) 1507–1516.
5. Ni H.,Wang Y.,Xu G.,Shao Z.,Zhang W., and Zhou X., “Multiscale Fine-Grained Heart Rate Variability Analysis for Recognizing the Severity of Hypertension,” Comput. Math. Methods Med., vol. 2019, 2019, doi: 10.1155/2019/4936179.
6. Hermida R.C., Smolensky M.H., Ayala D.E., Portaluppi F., Ambulatory Blood Pressure Monitoring (ABPM) as the reference standard for diagnosis of hypertension and assessment of vascular risk in adults, Chronobiol. Int. 32 (10) (2015) 1329–1342.
7. Khan M.U.,Aziz S.,Akram T.,Amjad F.,Iqtidar K.,Nam Y.,Khan M.A., Expert Hypertension Detection System Featuring Pulse Plethysmograph Signals and Hybrid Feature Selection and ReductionScheme,Sensors,21,2021,1,247,doi:10.3390/s21010247,htGPs://www.mdpi.com/14248220/21/1/247
8. Rajput J.S.,Sharma M.,Tan R.S., Acharya UR. Automated detection of severity of hypertension ECG signals using an optimal bi-orthogonal wavelet filter bank. Comput Biol Med. 2020 Aug;123:103924. doi: 10.1016/j.compbiomed.2020.103924. Epub 2020 Jul 23. PMID: 32768053.

9. Soh D.C.K.,Ng E.Y.K.,Jahmunah V.,Oh S.L.,Tan R.S.,Acharya U.R., Automated diagnostic tool for hypertension using convolutional neural network, Computers in Biology and Medicine,Volume 126,2020,103999,ISSN 0010-4825, htGPs://doi.org/10.1016/j.compbiomed.2020.103999.
10. Poddar M.G.,Kumar V.,Sharma Y.P.,Linear-nonlinear heart rate variability analysis and SVM based classification of normal and hypertensive subjects, Journal of Electrocardiology,Volume 46, Issue 4,2013,Page e25,ISSN 0022-0736.
11. Moody G.B., Mark R.G., Goldberger A.L., PhysioNet: physiologic signals, time series and related open source software for basic, clinical, and applied research, Conf. Proc. IEEE Eng. Med. Biol. Soc. 2011 (2011) 8327–8330. Cambridge, MA 20139, USA.
12. Melillo P., Izzo R., Orrico A., Scala P., Attanasio M., Mirra M., Luca N.D.,Pecchia L., Automatic prediction of cardiovascular and cerebrovascular events using Heart Rate Variability analysis, PloS One (2015). March 20.
13. Huang N. E., Shen Z., Long S. R., Wu M. C., Shih H. H., Zheng Q., Yen N.-C., Tung C. C., and Liu H. H.,“The empirical mode decomposition and the Hilbert spectrum for non-linear and non stationary time series analysis,” Proc. Royal Soc. London A, vol. 454, pp. 903–995, Mar. 1998.
14. Rilling G., Flandrin P., and Gonçalves P., “On empirical mode decomposition and its algorithms,” in Proc. IEEE-EURASIP Workshop Nonlinear Signal Image Process., Jun. 2003, pp. 1–5.
15. Kannathal N.,Choo M.L.,Acharya U.R.,Sadasivan P.K., Entropies for detection of epilepsy in EEG,Computer Methods and Programs in Biomedicine, Volume 80, Issue 3,2005,Pages 187-194, ISSN 0169-2607, htGPs://doi.org/10.1016/j.cmpb.2005.06.012.
16. Sabeti M.,Katebi S.,Boostani R., Entropy and complexity measures for EEG signal classification of schizophrenic and control participants, Artificial Intelligence in Medicine,Volume 47, Issue 3,2009,Pages 263-274,ISSN 0933-3657, htGPs://doi.org/10.1016/j.artmed.2009.03.003.
17. Lin J., "Divergence measures based on the Shannon entropy," in IEEE Transactions on Information Theory, vol. 37, no. 1, pp. 145-151, Jan. 1991, doi: 10.1109/18.61115.
18. Vapnik V. N., "An overview of statistical learning theory," in IEEE Transactions on Neural Networks, vol. 10, no. 5, pp. 988-999, Sept. 1999, doi: 10.1109/72.788640.
19. Kaya D., Turk M., Kaya T. , “Examining the Effect of Dimension Reduction on EEG Signals by K-Nearest Neighbors Algorithm” El-Cezerî Journal of Science and Engineering, 2018, 5(2); 591-595.
20. Narin A.,Özer M.,İşler Y.,"Effect of linear and non-linear measurements of heart rate variability in prediction of PAF attack," 2017 25th Signal Processing and Communications Applications Conference (SIU), 2017, pp. 1-4, doi: 10.1109/SIU.2017.7960358.
21. Erdoğan Y. E.,Narin A.,"Performance of Emprical Mode Decomposition in Automated Detection of Hypertension Using Electrocardiography," 2021 29th Signal Processing and Communications Applications Conference (SIU), 2021, pp. 1-4, doi: 10.1109/SIU53274.2021.9477887.
22. Erdoğan Y. E., Narin,COVID-19 detection with traditional and deep features on cough acoustic signals, Computers in Biology and Medicine,Volume 136,2021,104765,ISSN 0010-4825, htGPs://doi.org/10.1016/j.compbiomed.2021.104765.
23. Isler Y., Narin A. and Ozer M. (2015) Comparison of The Effects of Cross-Validation Methods on Determining Performances of Classifiers Used in Diagnosing Congestive Heart Failure. Measurement Science Review, 15 (4): 196-201.
24. Yarğı V., Postalcıoğlu S., “EEG İşareti Kullanılarak Bağımlılığa Yatkınlığın Makine Öğrenmesi Teknikleri ile Analizi ” El-Cezerî Fen ve Mühendislik Dergisi, 2021, 8(1); 142-154.