SavedAdd your journal

Journals / Karaelmas Fen ve Mühendislik Dergisi / 2023 / Cilt: 13 Sayı: 1

The Effect of Heart Rate and Feature Normalization Methods to Diagnose Paroxysmal Atrial Fibrillation Using 30-Minute Heart Rate Variability Analysis

Paroksismal Atriyal Fibrilasyonun 30 Dakikalık Kalp Hızı Değişkenliği Analizi Kullanılarak Teşhisinde Kalp Hızı ve Öznitelik Normalizasyon Yöntemlerinin Etkisi

Murat Sürücü(TC MİLLİ EĞİTİM BAKANLIĞI NECATİBEY)0000-0002-9889-9952
Yalçın İşler(İZMİR KATİP ÇELEBİ ÜNİVERSİTESİ)0000-0002-2150-4756
Resul Kara(DÜZCE ÜNİVERSİTESİ)0000-0001-8902-6837
Pages
191–204
Publication Date
2023-06-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

As a result of this study, we proved a new potential use of the heart rate normalization method in the diagnosis of PAF.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Paroxysmal Atrial Fibrillation (PAF) is the initial stage of the Atrial Fibrillation that is one of the most common arrhythmia types.
📊
Key Findings & Data:Although it does not threaten the life directly, it triggers the fatal disorders and it increases the risk of stroke.
💡
Conclusion & Impact:As a result of this study, we proved a new potential use of the heart rate normalization method in the diagnosis of PAF.
🔬Design:Araştırma Makalesi
📍Scope:Comprehensive Sample
⚙️Variables:Paroksismal atriyal fibrilasyon · Kalp hızı değişkenliği · Normalizasyon

Abstract

Paroxysmal Atrial Fibrillation (PAF) is the initial stage of the Atrial Fibrillation that is one of the most common arrhythmia types. Although it does not threaten the life directly, it triggers the fatal disorders and it increases the risk of stroke. Therefore, it is essential to diagnose PAF as earlier as possible. For this purpose, there are many routine tests and pattern recognition based studies. In this study, we investigated the heart rate normalization method with its combination to feature normalization methods in the automatic diagnosis of PAF patients. First, Atrial Fibrillation Prediction Database, consisting of 30-minute ECG recordings and having open-access, was used to determine heart rate variability (HRV) data. Next, time-domain, frequency-domain, wavelet transform, and nonlinear features were extracted from both HRV and heart rate normalized HRV (HRN) data. These extracted features were normalized by MinMax and z-score methods. Hence, these six feature combinations of features directly and normalized versions from both HRV and HRN data were applied to the inputs of k-nearest neighbors (kNN) and multi-layer perceptron (MLP) classifier algorithms. Throughout the classifiers, features were selected using genetic algorithms. This study resulted in 81.00% accuracy with MinMax normalization using kNN algorithm and 91.92% accuracy with z-score normalization using MLP algorithm in HRV data. After applying the heart rate normalization, this study achieved 86.00% accuracy with z-score normalization using kNN algorithm and 95.96% accuracy with z-score normalization using MLP algorithm in HRN data. These results are higher than the other previous studies. The combination of heart rate normalization, Z-Score feature normalization, and multi-layer perceptron classifier outperforms the other studies related to automatic diagnosis of PAF in the literature. As a result of this study, we proved a new potential use of the heart rate normalization method in the diagnosis of PAF.

Özet

Paroksismal Atriyal Fibrilasyon (PAF), en yaygın ritim bozukluğu türlerinden olan Atriyal Fibrilasyon’un başlangıç aşamasıdır. Doğrudan hayatı tehdit etmiyor olmasına rağmen, ölümcül rahatsızlıkları tetiklemekte ve inme riskini artırmaktadır. Bu nedenle, PAF’ın mümkün olduğunca erken teşhisi önemlidir. Bu amaçla geliştirilmiş birçok rutin test ve örüntü tanıma tabanlı çalışma mevcuttur. Bu çalışmada, PAF hastalarının kalp hızı değişkenliği (KHD) analizi ile otomatik teşhisinde kalp hızı normalizasyonu ile öznitelik normalizasyonu yöntemlerinin birlikte etkisi incelenmiştir. Öncelikle, 30 dakikalık EKG kayıtlarını içeren açık erişimli Atrial Fibrillation Prediction veritabanı kullanılarak KHD verileri elde edilmiştir. Daha sonra, zaman alanı, frekans alanı, dalgacık dönüşümü ve doğrusal olmayan öznitelikler hem KHD verileri hem de kalp hızı normalize edilmiş KHD (NKHD) veriler kullanılarak hesaplanmıştır. Bu çıkarılan öznitelikler MinMax ve z-skor yöntemleri kullanılarak normalize edilmiştir. Böylece KHD ve NKHD ile elde edilen öznitelikler ile bunların normalize halleri olan bu altı öznitelik kombinasyonu, k yakın komşu (kNN) ve çok katmanlı algılayıcı (MLP) sınıflandırıcı girişlerine uygulanmıştır. Bu sınıflandırıcılarla birlikte genetik algoritma kullanılarak öznitelik seçimi yapılmıştır. KHD verilerinin kullanılması halinde, kNN algoritması kullanılarak MinMax normalizasyonu ile %81,00 sınıflandırıcı başarımına ve MLP algoritması kullanılarak z-skor normalizasyonu ile %91,92 başarıma ulaşılmıştır. Kalp hızı normalizasyonu uygulandıktan sonra, NKHD verilerinin kullanılması halinde, kNN algoritması kullanılarak z-skor normalizasyonu ile %86,00 sınıflandırıcı başarımına ve MLP algoritması kullanılarak z-skor normalizasyonu ile %95,96 başarıma ulaşılmıştır. Bu sonuçlar önceki benzer çalışmalardan daha başarılı sonuçlardır. Kalp hızı normalizasyonu, z-skor öznitelik normalizasyonu ve MLP sınıflandırıcı kombinasyonu literatürdeki otomatik PAF teşhisi çalışmalarının başarımlarını geçmiştir. Bu çalışmanın sonucunda, PAF teşhisinde kalp hızı normalizasyonu yönteminin potansiyel kullanımı ispatlanmıştır.

🔖

Cite This Article

Sürücü, M., İşler, Y., Kara, R., *, Y. İ. (2023). The Effect of Heart Rate and Feature Normalization Methods to Diagnose Paroxysmal Atrial Fibrillation Using 30-Minute Heart Rate Variability Analysis. Karaelmas Fen ve Mühendislik Dergisi, Cilt: 13 Sayı: 1, 191–204. https://doi.org/10.7212/karaelmasfen.1240840

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (52)

  1. Ahmad, S., Tejuja, A., Newman, K. D., Zarychanski, R., & Seely, A. J. 2009. Clinical review: a review and analysis of heart rate variability and the diagnosis and prognosis of infection. Critical care (London, England), 13: 232. https:// doi.org/10.1186/cc8132
  2. Asl, B. M., Setarehdan, S. K., Mohebbi, M. 2008. Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal, Artificial Intelligence in Medicine, 44: 51-64. https://doi.org/10.1016/j. artmed.2008.04.007
  3. Benjamin, E. J., Levy, D., Vaziri, S. M., D’Agostino, R. B., Belanger, A. J., Wolf, P. A. 1994. Independent risk factors for atrial fibrillation in a population-based cohort. The Framingham Heart Study. JAMA, 271: 840–844.
  4. Boon, K. H., Khalil-Hani, M., Malarvili, M. B., Sia, C. W. 2016. Paroxysmal Atrial Fibrillation Prediction Method with Shorter HRV Sequences. Computer Methods and Programs in Biomedicine, Elsevier BV, 187–196. https://doi.org/10.1016/j. cmpb.2016.07.016.
  5. Boon, K. H., Khalil-Hani, M., Malarvili, M. B. 2018. Paroxysmal Atrial Fibrillation Prediction Based on HRV Analysis and Non-Dominated Sorting Genetic Algorithm III. Computer Methods and Programs in Biomedicine, 153: 171–184. https://doi.org/10.1016/j.cmpb.2017.10.012
  6. Boon, K.H., Khalil-Hani, M., Sia, C.W. 2019. Paroxysmal Atrial Fibrillation Onset Prediction Using Heart Rate Variability Analysis and Genetic Algorithm for Optimization, In Proceedings of the International Conference on Data Engineering, 609-617. https://doi.org/10.1007/978-981-13- 1799-6_62
  7. Brennan, M., Palaniswami, M., Kamen, P. 2001. Do Existing Measures of Poincare Plot Geometry Reflect Nonlinear Features of Heart Rate Variability?. IEEE Transactions on Biomedical Engineering, Institute of Electrical and Electronics Engineers (IEEE), 48: 1342–1347. https://doi. org/10.1109/10.959330.
  8. Bulut, A., Ozturk, G., Kaya, I. 2022. Classification of sleep stages via machine learning algorithms. Journal of Intelligent Systems with Applications, 5(1): 66-70. https://doi.org/10.54856/ jiswa.202205210
  9. Chesnokov, Yuriy V. 2008. Complexity and spectral analysis of the heart rate variability dynamics for distant prediction of paroxysmal atrial fibrillation with artificial intelligence methods. Artificial Intelligence in Medicine, 43/2: 151–165. http://dx.doi.org/10.1016/j.artmed.2008.03.009.
  10. Chessa, M., Butera, G., Lanza, G. A., Bossone, E., Delogu, A., De Rosa, G., Marietti, G., Rosti, L., Carminati, M. 2002. Role of Heart Rate Variability in the Early Diagnosis of Diabetic Autonomic Neuropathy in Children. Herz, Springer Science and Business Media LLC, 27: 785–790. https://doi. org/10.1007/s00059-002-2340-4.
  11. Costin, H., Rotariu, C., Pasarica, A. 2013. Atrial fibrillation onset prediction using variability of ECG signals. 2013 8th International Symposium on Advanced Topics in Electrical Engineering (ATEE), IEEE. 1-4 https://doi.org/10.1109/ atee.2013.6563419.
  12. Duda, R.O., Hart, P.E., Stork, D.G. 2001. Pattern Classification, 2. Basım, John Wiley & Sons, New York, 688s.
  13. Duverney, D., Gaspoz, J.-M., Pichot, V., Roche, F., Brion, R., Antoniadis, A., Barthelemy, J.-C. 2002. High Accuracy of Automatic Detection of Atrial Fibrillation Using Wavelet Transform of Heart Rate Intervals. Pacing and Clinical Electrophysiology, Wiley, 25: 457–462. https://doi. org/10.1046/j.1460-9592.2002.00457.x.
  14. Ebrahimzadeh, E., Kalantari, M., Joulani, M., Shahraki, R. S., Fayaz, F., Ahmadi, F. 2018. Prediction of paroxysmal Atrial Fibrillation: A machine learning based approach using combined feature vector and mixture of expert classification on HRV signal. Computer Methods and Programs in Biomedicine, 165: 53–67. https://doi.org/10.1016/j.cmpb.2018.07.014
  15. Electrophysiology, T. F. of the E. S. of C. the N. A. 1996. Heart Rate Variability. Circulation, 93: 1043–1065. https://doi. org/10.1161/01.cir.93.5.1043
  16. Goldenberg, I., Goldkorn, R., Shlomo, N., Einhorn, M., Levitan, J., Kuperstein, R., Klempfner, R., Johnson, B. 2019. Heart Rate Variability for Risk Assessment of Myocardial Ischemia in Patients without Known Coronary Artery Disease: The HRV‐DETECT Study. Journal of the American Heart Association. https://doi.org/10.1161/jaha.119.014540.
  17. Gunduz, A. F., Talu, M. F. 2023. Atrial fibrillation classification and detection from ECG recordings, Biomedical Signal Processing and Control, 82:104531. https://doi.org/10.1016/j. bspc.2022.104531
  18. Hallstrom, A. P., Stein, P. K., Schneider, R., Hodges, M., Schmidt, G., Ulm, K. 2004. Structural Relationships Between Measures Based on Heart Beat Intervals: Potential for Improved Risk Assessment. IEEE Transactions on Biomedical Engineering, IEEE, 51: 1414–1420. https://doi. org/10.1109/tbme.2004.828049
  19. Hickey, B., Heneghan, C. 2002. Screening for paroxysmal atrial fibrillation using atrial premature contractions and spectral measures, Computers in Cardiology, 29:217-220, https://doi. org/10.1109/cic.2002.1166746
  20. Huang, Y. H., Lyle, J. V., Ab Razak, A. S., Nandi, M., Marr, C. M., Huang, C. L.-H., Aston, P. J., Jeevaratnam, K. 2022. Detecting paroxysmal atrial fibrillation from normal sinus rhythm in equine athletes using Symmetric Projection Attractor Reconstruction and machine learning. Cardiovascular Digital Health Journal, 3:96–106. https://doi. org/10.1016/j.cvdhj.2022.02.001
  21. Isler, Y., Kuntalp, M. 2009. Heart rate normalization in the analysis of heart rate variability in congestive heart failure. Proceedings of the Institution of Mechanical Engineers, Part H: Journal of Engineering in Medicine, SAGE Publications, 224: 453–463. https://doi.org/10.1243/09544119jeim642.
  22. Isler, Y., Narin, A., Ozer, M., Perc, M. 2019. Multi-stage classification of congestive heart failure based on shortterm heart rate variability. Chaos, Solitons & Fractals, Elsevier BV, 118: 145–151. https://doi.org/10.1016/j. chaos.2018.11.020
  23. Ke, J.-Q., Shao, S.-M., Zheng, Y.-Y., Fu, F.-W., Zheng, G.- Q., Liu, C.-F. 2017. Sympathetic skin response and heart rate variability in predicting autonomic disorders in patients with Parkinson disease. Medicine, 96: e6523. https://doi. org/10.1097/md.0000000000006523
  24. Langley, P., di Bernardo, D., Allen, J., Bowers, E., Smith, F. E., Vecchietti, S., Murray, A. 2001. Can paroxysmal atrial fibrillation be predicted? Computers in Cardiology. 28:121- 124, https://doi.org/10.1109/cic.2001.977606.
  25. Lee, M.Y., Yu, S.N. 2012. Multiscale sample entropy based on discrete wavelet transform for clinical heart rate variability recognition. Engineering in Medicine and Biology Society, 4299- 4302, https://doi.org/10.1109/embc.2012.6346917, 2012. Lip, G. Y. H. 2001. Paroxysmal atrial fibrillation. QJM, 94: 665– 678. https://doi.org/10.1093/qjmed/94.12.665
  26. Maghawry, E., Ismail, R., Gharib, T. F. 2021. An efficient approach for Paroxysmal Atrial Fibrillation events prediction using Extreme Learning Machine. Journal of Intelligent & Fuzzy Systems, 40:5087–5099. https://doi.org/10.3233/jifs- 201832
  27. Mohebbi, M., Ghassemian, H. 2012. Prediction of paroxysmal atrial fibrillation based on non-linear analysis and spectrum and bispectrum features of the heart rate variability signal. Computer Methods and Programs in Biomedicine, Elsevier BV, 105: 40–49. https://doi.org/10.1016/j.cmpb.2010.07.011.
  28. Moody, G., Goldberger, A., McClennen, S., Swiryn, S. 2001. Predicting the onset of paroxysmal atrial fibrillation: The Computers in Cardiology Challenge 2001, 28: 113-116. https://doi.org/10.1109/cic.2001.977604
  29. Moran, P. S., Teljeur, C., Harrington, P., Smith, S. M., Smyth, B., Harbison, J., Normand, C., Ryan, M. 2016. Cost- Effectiveness of a National Opportunistic Screening Program for Atrial Fibrillation in Ireland. Value in Health, Elsevier BV, 19: 985–995. https://doi.org/10.1016/j.jval.2016.07.007
  30. Narin, A., Isler, Y., Ozer, M. 2016. Early prediction of Paroxysmal Atrial Fibrillation using frequency domain measures of heart rate variability. Medical Technologies National Congress (TIPTEKNO), IEEE, 1-4 https://doi.org/10.1109/tiptekno. 2016.7863110
  31. Narin, A., Isler, Y., Ozer, M., Perc, M. 2018. Early prediction of paroxysmal atrial fibrillation based on short-term heart rate variability. Physica A: Statistical Mechanics and its Applications, 509:56–65. https://doi.org/10.1016/j.physa.2018.06.022
  32. Narin, A., Isler, Y., Ozer, M. 2019. Early prediction of paroxysmal atrial fibrillation using wavelet transform methods. Journal of Intelligent Systems with Applications, 2(2): 111-114. https:// doi.org/10.54856/jiswa.201912077
  33. Ozcan, N., Kuntalp, M. 2017. Determining best HRV indices for PAF screening using genetic algorithm, 10th International Conference on Electrical and Electronics Engineering Pappano, A.J., Wier, W.G. 2019. Cardiovascular Physiology, 11. Basım, Elsevier, 300s.
  34. Park, J., Lee, S., Jeon, M. 2009. Atrial fibrillation detection by heart rate variability in Poincare plot. BioMedical Engineering OnLine, Springer Science and Business Media LLC., 8:38, https://doi.org/10.1186/1475-925x-8-38
  35. Parsa, S. F., Vafajoo, A., Rostami, A., Salarian, R., Rabiee, M., Rabiee, N., Rabiee, G., Tahriri, M., Yadegari, A., Vashaee, D., Tayebi, L., Hamblin, M. R. 2018. Early diagnosis of disease using microbead array technology: A review. Analytica Chimica Acta, 1032: 1–17. https://doi.org/10.1016/j. aca.2018.05.011
  36. Parsi, A., Glavin, M., Jones, E., Byrne, D. 2021. Prediction of paroxysmal atrial fibrillation using new heart rate variability features. Computers in Biology and Medicine, 133:104367. https://doi.org/10.1016/j.compbiomed.2021.104367
  37. Pothineni, N. V. K., Deo, R. 2020. Screening for Atrial Fibrillation. Circulation, 135: 1523–1526. https://doi. org/10.1161/circulationaha.120.046298.
  38. Rouhani, M., Soleymani, R. 2009. Neural Networks Based Diagnosis of Heart Arrhythmias Using Chaotic and Nonlinear Features of HRV Signals. 2009 International Association of Computer Science and Information Technology - Spring Conference, 545-549. https://doi.org/10.1109/iacsit-sc.2009.23
  39. Ryder, K. M., Benjamin, E. J. 1999. Epidemiology and significance of atrial fibrillation. The American Journal of Cardiology, 84: 131–138. https://doi.org/10.1016/s0002-9149(99)00713-4
  40. Salinet, J. L., Madeiro, J. P. V., Cortez, P. C., Stafford, P. J., André Ng, G., Schlindwein, F. S. 2013. Analysis of QRS-T subtraction in unipolar atrial fibrillation electrograms. Medical & Biological Engineering & Computing, 51: 1381–1391. https://doi.org/10.1007/s11517-013-1071-4
  41. Seker, R., Saliu, S., Birand, A., Kudaiberdieva, G. 2000. Validity test for a set of nonlinear measures for short data length with reference to short-term heart rate variability signal, Journal of Systems Integration, 10: 41-53. https://doi. org/10.1023/A:1026507317626
  42. Sepulveda-Suescun, J. P., Murillo-Escobar, J., Urda-Benitez, R. D., Orrego-Metaute, D. A., Orozco-Duque, A. 2017. Atrial fibrillation detection through heart rate variability using a machine learning approach and Poincare plot features. VII Latin American Congress on Biomedical Engineering CLAIB, 60: 565–568. https://doi.org/10.1007/978-981-10- 4086-3_142
  43. Sessa, F., Anna, V., Messina, G., Cibelli, G., Monda, V., Marsala, G., Ruberto, M., Biondi, A., Cascio, O., Bertozzi, G., Pisanelli, D., Maglietta, F., Messina, A., Mollica, M. P., Salerno, M. 2018. Heart rate variability as predictive factor for sudden cardiac death. Aging, Impact Journals, 10: 166–177. https://doi.org/10.18632/aging.101386
  44. Soudani, A., Almusallam, M. 2018. Atrial Fibrillation detection based on ECG-Features Extraction in WBSN. Procedia Computer Science, 130: 472–479. https://doi.org/10.1016/j. procs.2018.04.052
  45. Steger, C., Pratter, A., Martinekbregel, M., Avanzini, M., Valentin, A., Slany, J., Stollberger, C. 2004. Stroke patients with atrial fibrillation have a worse prognosis than patients without: data from the Austrian Stroke registry. European Heart Journal, 25: 1734–1740. https://doi.org/10.1016/j. ehj.2004.06.030
  46. Surucu, M., Isler, Y., Perc, M., Kara, R. 2021. Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: Theory and applications. Chaos: An Interdisciplinary Journal of Nonlinear Science, 31(11): 113119. https://doi. org/10.1063/5.0069272
  47. Tsipouras, M. G., Fotiadis, D. I. 2004. Automatic arrhythmia detection based on time and time–frequency analysis of heart rate variability. Computer Methods and Programs in Biomedicine, 74: 95–108. https://doi.org/10.1016/s0169- 2607(03)00079-8
  48. Verde, L., De Pietro, G. 2019. A neural network approach to classify carotid disorders from Heart Rate Variability analysis. Computers in Biology and Medicine, 109: 226–234. https:// doi.org/10.1016/j.compbiomed.2019.04.036
  49. Wang, L.-H., Yan, Z.-H., Yang, Y.-T., Chen, J.-Y., Yang, T., Kuo, I.-C., Abu, P. A. R., Huang, P.-C., Chen, C.-A., Chen, S.-L. 2021. A Classification and Prediction Hybrid Model Construction with the IQPSO-SVM Algorithm for Atrial Fibrillation Arrhythmia. Sensors, 21:5222. https://doi. org/10.3390/s21155222
  50. Webster, G. 2010. Medical Instrumentation: Application and Design, 4. Edition, Wiley, 675s.
  51. Wilkins, E., Wilson, L., Wickramasinghe, K., Bhatnagar, P., Leal, J., Luengo-Fernandez, R., Burns, R., Rayner, M., Townsend, N. 2017. European Cardiovascular Disease Statistics, European Heart Network
  52. Xiong, P., Li, J., Liu, M., Zhang, J., Yang, J., Zhang, H., Du, H., Liu, X. 2022. Short-Term Paroxysmal Atrial Fibrillation Detection with Intra- and Inter-Patient Paradigm Based on R-R Intervals. SSRN Electronic Journal, https://doi. org/10.2139/ssrn.4098697