An ECG Segmentation Method Based on GMM and Clusterwise Regression

Abstract

The electrocardiogram (ECG) segmentation needs to separate different waves from an ECG and cluster the waves simultaneously. Clusterwise regression is a useful approach that can segment and cluster the data simultaneously. In this paper, we apply the clusterwise regression method to segment the ECG. By modeling the ECG signal wave by the Gaussian mixture model (GMM) and introducing a weight function, we propose a minimization model that consists of the weighted sum of the negative log-likelihood and the total variation (TV) of the weight function. The TV of the weight function enforces the temporal consistency. A supervised algorithm is designed to solve the proposed model. Experimental results show the efficiency of the proposed method for the ECG segmentation.

Keywords

Electrocardiogram (ECG) / Segmentation / Fiducial point extraction / Gaussian mixture model (GMM) / Clusterwise regression / 92C55 / 62H30 / 62R07

References

[1] AkhbariM, ShamsollahiMB, SayadiO, ArmoundasAA, JuttenC. ECG segmentation and fiducial point extraction using multi hidden Markov model. Comput. Biol. Med., 2016, 79: 21-29

[2] CurtinAE, BurnsKV, BankAJ, NetoffTI. QRS complex detection and measurement algorithms for multichannel ECGs in cardiac resynchronization therapy patients. IEEE J. Transl. Eng. Health. Med., 2018, 6: 1-11

[3] Fujita, N., Sato, A., Kawarasaki, M.: Performance study of wavelet-based ECG analysis for ST-segment detection. In: 2015 38th International Conference on Telecommunications and Signal Processing (TSP), pp. 430–434 (2015)

[4] Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P.C., Mark, R., Mietus, J.E., Moody, G.B., Peng, C.K., Stanley, H.E.: PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220 (2000)

[5] GoovaertsG, PadhyS, VandenberkB, VaronC, WillemsR, Van HuffelS. A machine-learning approach for detection and quantification of QRS fragmentation. IEEE J. Biomed. Health. Inform., 2019, 23(5): 1980-1989

[6] Hadjem, M., Nalït-Abdesselam, F., Khokhar, A.: ST-segment and T-wave anomalies prediction in an ECG data using RUSBoost. In: 2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom), pp. 1–6 (2016)

[7] Hallac, D., Vare, S., Boyd, S., Leskovec, J.: Toeplitz inverse covariance-based clustering of multivariate time series data. In: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, vol. 2017, pp. 215–223 (2017)

[8] Hu, J.-L., Bao, S.-D.: An approach to QRS complex detection based on multiscale mathematical morphology. In: 2010 3rd International Conference on Biomedical Engineering and Informatics, vol. 2, pp. 725–729 (2010)

[9] Laguna P., Mark R.G., Goldberger A.L., Moody G.B.: A database for evaluation of algorithms for measurement of QT and other waveform intervals in the ECG. Computers in Cardiology 24, 673–676 (1997)

[10] Makowski, D., Pham, T., Lau, Z.J., Brammer, J., Lespinasse, F., Pham, H., Schölzel, C., Chen, S.: NeuroKit2: a Python toolbox for neurophysiological signal processing. Behav. Res. Methods 53, 1689–1696 (2021)

[11] Di Marco, L.Y., Chiari, L.: A wavelet-based ECG delineation algorithm for 32-bit integer online processing. Biomed. Eng. Online 10, 23–23 (2011)

[12] MartisRJ, ChakrabortyC, RayAK. A two-stage mechanism for registration and classification of ECG using Gaussian mixture model. Pattern. Recognit., 2009, 42(11): 2979-2988

[13] McSharryPE, CliffordGD, TarassenkoL, SmithLA. A dynamical model for generating synthetic electrocardiogram signals. IEEE Trans. Biomed. Eng., 2003, 50(3): 289-294

[14] Mneimneh, M.A., Povinelli, R.J.: RPS/GMM approach toward the localization of myocardial infarction. In: 2007 Computers in Cardiology, pp. 185–188 (2007)

[15] Sehirli, E., Turan, M.K.: A novel method for segmentation of QRS complex on ECG signals and classify cardiovascular diseases via a hybrid model based on machine learning. Int. J. Intell. Syst. Appl. Eng. 9(1), 12–21 (2021)

[16] SpathH. Clusterwise linear regression. Computing, 1979, 22: 367-373

[17] SukHW, HwangH. Regularized fuzzy clusterwise ridge regression. Adv. Data Anal. Classif., 2010, 4: 35-51

[18] Terzı, M.B., Arikan, O.: Detection of myocardial ischaemia by using ECG, artificial neural network and Gaussian mixture model. In: 2020 28th Signal Processing and Communications Applications Conference (SIU), pp. 1–4 (2020)

[19] Thomas, J., Rose, C., Charpillet, F.: A support system for ECG segmentation based on hidden Markov models. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3228–3231 (2007)

[20] UmerM, BhattiBA, TariqMH, Zia-ul-HassanM, KhanMY, ZaidiT. Electrocardiogram feature extraction and pattern recognition using a novel windowing algorithm. Adv. Biosci. Biotechnol., 2014, 05: 886-894

[21] XiaoR, XuY, PelterMM, FidlerRL, BadiliniF, MortaraDW, HuX. Monitoring significant ST changes through deep learning. J. Electrocardiol., 2018, 51(6S): 78-82

[22] XuM, WeiS, QinX, ZhangY, LiuC. Rule-based method for morphological classification of ST segment in ECG signals. J. Med. Biol. Eng., 2015, 35: 816-823

Funding

National Natural Science Foundation of China(11971215)

RIGHTS & PERMISSIONS

Shanghai University