Kalp Ritim Bozukluklarının Çok Sınıflı Sınıflandırılmasında ReliefF Yöntemi ve Makine Öğrenimi Tabanlı Yaklaşım

Abstract

Kardiyovasküler hastalıklar (KVH), dünya genelinde ciddi sağlık tehditleri arasında yer almakta ve tüm ölümlerin yaklaşık %32'sine neden olmaktadır. Bu nedenle, KVH'ların erken tanısı ve uygun tedaviye başlanması hayati önem taşımaktadır. Elektrokardiyografi (EKG), kalbin elektriksel aktivitesinin kaydedilmesiyle elde edilen önemli bir tanı yöntemidir. Ancak, aritmi gibi kalp rahatsızlıklarının tanısı, uzman klinisyenlerin gözle incelemesine dayanmakta ve bu süreç zaman alıcı ve zahmetli olabilmektedir. Bu çalışmada, EKG sinyallerinden otomatik aritmi tespiti için bir bilgisayar destekli sistem geliştirilmesi amaçlanmıştır. Normal sinüs ritmi, pacemaker ritmi ve 15 farklı aritmi olmak üzere toplam 17 farklı kardiyak aktivite; EKG sinyallerinden çok çeşitli öznitelik çıkarımı, ReliefF kullanılarak öznitelik seçimi ve farklı makine öğrenimi algoritmalarını kullanılması ile sınıflandırılmıştır. Elde edilen sonuçlar, K-En Yakın Komşu ve Rastgele Orman algoritmalarının %93,4 ve %99,23 doğruluk oranları ile en yüksek başarıyı gösterdiğini ortaya koymuştur. Bu çalışma, aritmilerin çok sınıflı sınıflandırmasında EKG sinyallerinden morfolojik, zaman, frekans, entropi ve karmaşıklık özniteliklerini bir arada çıkararak, farklı makine öğrenimi algoritmaları kullanarak 17 farklı kardiyak aktivite sınıfını yüksek doğruluk oranlarıyla sınıflandırmıştır. Böylece, literatürdeki çalışmalardan farklılaşarak aritminin otomatik sınıflandırılmasına önemli bir katkı sağlamıştır.

Keywords

• Elektrokardiyogram
• Aritmi
• Öznitelik seçimi
• ReliefF
• Makine öğrenimi
• Sınıflandırma

The ReliefF Method and Machine Learning-Based Approach in the Multi-Class Classification of Cardiac Arrhythmias

Abstract

Cardiovascular diseases (CVDs) represent a significant health threat worldwide and account for approximately 32% of all deaths. Therefore, early diagnosis and timely treatment of CVDs are crucial. Electrocardiography (ECG) is an important diagnostic method that involves recording the electrical activity of the heart. However, the diagnosis of heart disorders, such as arrhythmias, relies on the visual examination of expert clinicians, making this process time-consuming and labor-intensive. This study aims to develop a computer-assisted system for automatic arrhythmia detection from ECG signals. A total of 17 different cardiac activities, including normal sinus rhythm, pacemaker rhythm, and 15 different arrhythmias, were classified using various feature extraction methods from ECG signals, feature selection through ReliefF, and different machine learning algorithms. The results obtained show that the K-Nearest Neighbors and Random Forest algorithms achieved the highest accuracies of 93.4% and 99.23%, respectively. This study distinguishes itself from existing literature by extracting morphological, temporal, frequency, entropy, and complexity features from ECG signals for multi-class classification of arrhythmias and successfully classifying the 17 different cardiac activity classes with high accuracy. Thus, it provides a significant contribution to the automatic classification of arrhythmias.

Keywords

• Electrocardiogram
• Arrhythmia
• Feature selection
• ReliefF
• Machine learning
• Classification

References

1. Afaq Y, Manocha A. 2024. Blockchain and deep learning integration for various application: a review. JCIS, 64: 92-105.
2. Allabun S. 2024. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. IJACSA, 15: 4.
3. Alqudah AM, Alqudah A. 2022. Deep learning for single-lead ECG beat arrhythmia-type detection using novel iris spectrogram representation. Soft Comput, 26: 1123-1139.
4. Altıntop ÇG, Latifoğlu F, Akın AK. 2022. Can patients in deep coma hear us? Examination of coma depth using physiological signals. Biomed Signal Process Control, 77: 103756.
5. Bishop CM, Nasrabadi NM. 2006. Pattern recognition and machine learning. Springer, New York, USA, pp: 738.
6. Breiman L. 2001. Random forests. Machine learning, 45: 5-32.
7. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP. 2002. SMOTE: Synthetic minority over-sampling technique. JAIR, 16: 321-357.
8. Cortes C, Vapnik V. 1995. Support-vector networks. Mach Learn, 20(3): 273-297.

9. Das MK, Ari S. 2014. Electrocardiogram beat classification using S-transform based feature set. JMMB, 14:1450066.
10. Daydulo YD, Thamineni B, Dawud AA. 2023. Cardiac arrhythmia detection using deep learning approach and time frequency representation of ECG signals. BMC Med Inform Decis Mak, 23: 232.
11. Demiroğlu U, Şenol B, Matušů R. 2024. A fused electrocardiography arrhythmia detection method. Multim Tools Appl, 83: 49057-49089.
12. Devadas RM. 2021. Cardiac arrhythmia classification using svm, knn and naive bayes algorithms. IRJET, 8(5): 3937-3941.
13. Dhyani S, Kumar A, Choudhury S. 2023. Analysis of ECG-based arrhythmia detection system using machine learning. MethodsX, 10: 102195.
14. Dinakarrao SMP., Jantsch A, Shafique M. 2019. Computer-aided arrhythmia diagnosis with bio-signal processing: A survey of trends and techniques. ACM CSUR, 52(2): 1-37.
15. Ebrahimi Z, Loni M, Daneshtalab M, Gharehbaghi A. 2020. A review on deep learning methods for ECG arrhythmia classification. Expert Syst Appl, 7: 100033.
16. Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Stanley HE. 2000. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 101(23): e215-e220.
17. Goldberger AL, Goldberger ZD, Shvilkin A. 2017. Clinical electrocardiography: a simplified approach: clinical electrocardiography: a simplified approach e-book. Elsevier Health Sciences, London, UK, pp: 187.
18. Gopinathannair R, Etheridge SP, Marchlinski FE, Spinale FG, Lakkireddy D, Olshansky B. 2015. Arrhythmia-induced cardiomyopathies: mechanisms, recognition, and management. JACC, 66(15): 1714-1728.
19. Gou J, Ma H, Ou W, Zeng S, Rao Y, Yang H. 2019. A generalized mean distance-based k-nearest neighbor classifier. Expert Syst Appl, 115: 356-372.
20. Gupta V, Mittal M. 2020. A novel method of cardiac arrhythmia detection in electrocardiogram signal. IJMEI, 12(5): 489-499.
21. Huang Z, Yang C, Zhou X, Huang T. 2018. A hybrid feature selection method based on binary state transition algorithm and ReliefF. IEEE J-BHI, 23(5): 1888-1898.
22. Huikuri HV, Castellanos A, Myerburg RJ. 2001. Sudden death due to cardiac arrhythmias. NEJM, 345(20): 1473-1482.
23. Inan OT, Giovangrandi L, Kovacs GTA. 2006. Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features. IEEE TBME, 53(12): 2507-2515.
24. Kira K, Rendell L. A. 1992. A practical approach to feature selection. Machine learning proceedings. Elsevier, Amsterdam, Holand, pp: 249-256.
25. Kohli N, Verma NK. 2011. Arrhythmia classification using SVM with selected features. IJEST, 3(8): 122-131.
26. Kononenko I. 1994. Estimating attributes: Analysis and extensions of RELIEF. European conference on machine learning proceedings. Springer, Berlin, Germany, pp: 171-182.
27. Kossmann CE. 1953. The normal electrocardiogram. Circulation, 8(6): 920-936.
28. Liou JW, Wang PS, Wu YT, Lee SK, Chang SD, Liou M. 2022. ECG approximate entropy in the elderly during cycling exercise. Sensors, 22(14): 5255.
29. Maldonado S, Weber R, Famili F. 2014. Feature selection for high-dimensional class-imbalanced data sets using support vector machines. Inf Sci, 286: 228-246.
30. Marinho LB, Nascimento NMM, Souza JWM, Gurgel MV, Rebouças Filho PP, de Albuquerque VHC. 2019. A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification. FGCS, 97: 564-577.
31. Martis RJ, Acharya UR, Adeli H. 2014. Current methods in electrocardiogram characterization. Comput Biol Med, 48: 133-149.
32. Martis RJ, Acharya UR, Lim CM, Mandana KM, Ray AK, Chakraborty C. 2013. Application of higher order cumulant features for cardiac health diagnosis using ECG signals. Int J Neural Syst, 23(04): 1350014.
33. Mazaheri V, Khodadadi H. 2020. Heart arrhythmia diagnosis based on the combination of morphological, frequency and nonlinear features of ECG signals and metaheuristic feature selection algorithm. Expert Syst Appl, 161: 113697.
34. Mian Qaisar S, Hussain SF. 2023. An effective arrhythmia classification via ECG signal subsampling and mutual information based subbands statistical features selection. J Ambient Intell Humaniz Comput, 14(3): 1473-1487.
35. Mishra A, Sahu SS, Sharma R, Mishra SK. 2021. Denoising of electrocardiogram signal using S-transform based time-frequency filtering approach. Arab J Sci Eng, 2021: 1-11.
36. Mitra M, Samanta RK. 2013. Cardiac arrhythmia classification using neural networks with selected features. Proc Technol, 10: 76-84.
37. Mizobuchi A, Osawa K, Tanaka M, Yumoto A, Saito H, Fuke S. 2021. Detrended fluctuation analysis can detect the impairment of heart rate regulation in patients with heart failure with preserved ejection fraction. Cardiol J, 77(1): 72-78.
38. Mondéjar-Guerra V, Novo J, Rouco J, Penedo MG, Ortega M. 2019. Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomed. Signal Process Control, 47: 41-48.
39. Moody GB, Mark RG. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol, 20(3): 45-50.
40. Nascimento NMM, Marinho LB, Peixoto SA, do Vale Madeiro JP, de Albuquerque VHC, Filho PPR. 2020. Heart arrhythmia classification based on statistical moments and structural co-occurrence. CSSP, 39(2): 631-650.
41. Oh SL, Ng EYK, San Tan R, Acharya UR. 2019. Automated beat-wise arrhythmia diagnosis using modified U-net on extended electrocardiographic recordings with heterogeneous arrhythmia types. Comput Biol Med, 105: 92-101.
42. Ojha MK, Wadhwani S, Wadhwani AK, Shukla A. 2022. Automatic detection of arrhythmias from an ECG signal using an auto-encoder and SVM classifier. Phys Eng Sci Med, 45(2): 665-674.
43. Organization WH 2021. Cardiovascular Diseases. URL: https://www.who.int/health-topics/cardiovascular-diseases#tab=tab_1 (accessed date: October 2, 2024)
44. Osowski S, Linh TH. 2001. ECG beat recognition using fuzzy hybrid neural network. IEEE Trans Biomed Eng, 48(11): 1265-1271.
45. Peng C, Havlin S, Stanley HE, Goldberger AL. 1995. Quantification of scaling exponents and crossover phenomena in nonstationary heartbeat time series. Chaos, 5(1): 82-87.
46. Pławiak P, Acharya UR. 2020. Novel deep genetic ensemble of classifiers for arrhythmia detection using ECG signals. Neural Comput Appl, 32(15):11137-11161.
47. Plawiak P. 2017. ECG signals (1000 fragments). Mendeley Data, v3, London, UK.
48. Pławiak P. 2018. Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system. Expert Syst Appl, 92: 334-349.
49. Rodriguez E, Lerma C, Echeverria JC, Alvarez-Ramirez J. 2008. ECG scaling properties of cardiac arrhythmias using detrended fluctuation analysis. Physiol Meas, 29(11): 1255.
50. Sahoo S, Subudhi A, Dash M, Sabut S. 2020. Automatic classification of cardiac arrhythmias based on hybrid features and decision tree algorithm. IJAC, 17(4): 551-561.
51. Samb ML, Camara F, Ndiaye S, Slimani Y, Esseghir MA. 2012. A novel RFE-SVM-based feature selection approach for classification. IJAST, 43(1): 27-36.
52. Sangaiah AK, Arumugam M, Bian GB. 2020. An intelligent learning approach for improving ECG signal classification and arrhythmia analysis. Artif Intell Med, 103:101788.
53. Sharma LD, Rahul J, Aggarwal A, Bohat VK. 2023. An improved cardiac arrhythmia classification using stationary wavelet transform decomposed short duration QRS segment and Bi-LSTM network. Multidimens Syst Signal Process, 34(2): 503-520.
54. Shi H, Wang H, Huang Y, Zhao L, Qin C, Liu C. 2019. A hierarchical method based on weighted extreme gradient boosting in ECG heartbeat classification. Comput Methods Programs Biomed, 171: 1-10.
55. Shilaskar S, Ghatol A. 2013. Feature selection for medical diagnosis: Evaluation for cardiovascular diseases. Expert Syst Appl, 40(10):4146-4153.
56. Singhal S, Kumar M. 2023. A systematic review on artificial intelligence-based techniques for diagnosis of cardiovascular arrhythmia diseases: challenges and opportunities. Arch Comput Methods Eng, 30(2): 865-888.
57. Tuncer T, Dogan S, Pławiak P, Acharya UR. 2019. Automated arrhythmia detection using novel hexadecimal local pattern and multilevel wavelet transform with ECG signals. Knowl-Based Syst, 186: 104923.
58. Vásquez-Iturralde F, Flores-Calero M, Grijalva-Arévalo F, Rosales-Acosta A. 2024. Automatic Classification of Cardiac Arrhythmias using Deep Learning Techniques: A Systematic Review. IEEE Access, 12: 118467-118492.
59. Wan X, Liu Y, Mei X, Ye J, Zeng C, Chen Y. 2024. A novel atrial fibrillation automatic detection algorithm based on ensemble learning and multi-feature discrimination. MBEC, 62(6): 1809-1820.
60. Wang D, Meng Q, Chen D, Zhang H, Xu L. 2020. Automatic detection of arrhythmia based on multi-resolution representation of ECG signal. Sensors, 20(6): 1579.
61. Yang H, Wei Z. 2020. Arrhythmia recognition and classification using combined parametric and visual pattern features of ECG morphology. IEEE Access, 8:47103-47117.
62. Yang J, Yan R. 2020. A multidimensional feature extraction and selection method for ECG arrhythmias classification. IEEE Sens J, 21(13): 14180-14190.
63. Yeh YC, Chiou CW, Lin HJ. 2012. Analyzing ECG for cardiac arrhythmia using cluster analysis. Expert Syst Appl, 39(1): 1000-1010.
64. Yıldırım Ö, Pławiak P, Tan RS, Acharya UR. 2018. Arrhythmia detection using deep convolutional neural network with long duration ECG signals. Comput Biol Med, 102: 411-420.
65. Zimetbaum P, Goldman A. 2010. Ambulatory arrhythmia monitoring: choosing the right device. Circulation, 122(16): 1629-1636.