Using Electrocardiogram Signal Features and Heart Rate Variability to Predict Epileptic Attacks

Ying  Jiang; Yuan  Feng; Danni  Lu; Lin  Yang; Qun  Zhang; Haiyan  Yang; Ning  Li

doi:10.6180/jase.202508_28(8).0017

Using Electrocardiogram Signal Features and Heart Rate Variability to Predict Epileptic Attacks

Ying Jiang, Yuan FengThis email address is being protected from spambots. You need JavaScript enabled to view it., Danni Lu, Lin Yang, Qun Zhang, Haiyan Yang, and Ning Li

Department of Neurology, Ruikang Hospital affiliated to Guangxi University of Chinese Medicine, Nanning, Guangxi, 530011, China

Received: August 22, 2024
Accepted: October 6, 2024
Publication Date: November 16, 2024

Copyright The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License (CC BY 4.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are cited.

Download Citation: ||https://doi.org/10.6180/jase.202508_28(8).0017

Since the increase in neuronal activity during an epileptic attack affects the voluntary nervous system, and the voluntary nervous system also affects the heart rate variability, it can be concluded that seizures can be predicted by monitoring heart rate variability. In this study, a new method for predicting epilepsy through the analysis of heart rate variability is proposed. In the proposed method, 12 features are extracted from the heart rate variability signal in time, frequency, time-frequency, and nonlinear domains to predict epileptic seizures. We used a multivariate statistical process control algorithm for abnormality detection. The presented algorithm was evaluated on a dataset consisting of 17 patients, where the obtained results show that the proposed method can predict epileptic attacks with an accuracy of 88.2%. From a practical point of view, due to the ease of obtaining the heart rate variability signal, the proposed algorithm is more promising than the algorithms that use brain signal processing to predict epilepsy.

Keywords: Disease diagnosis; Epilepsy; Heart rate; Signal processing; Multivariate statistical process

[1] B.Wu,(1967)“EmotionRecognitionBasedOnElectroen cephalogramSignalsUsingDeepLearningNetwork" JournalofAppliedScienceandEngineering27:DOI: https://doi.org/10.6180/jase.2024012_7(1).0014.
[2] D.Georgieva,J.Langley,K.Hartkopf,L.Hawk,A. Margolis,A.Struck,E.Felton,D.Hsu,andB.E.Gidal, (2023)“Real-world,long-termevaluationofthetolerabil ityandtherapyretentionofEpidiolex®(cannabidiol)in patientswithrefractoryepilepsy"Epilepsy&Behavior 141:109159.DOI: https://doi.org/10.1016/j.yebeh.2023.109159.
[3] M.Cheval,M.Houot,N.Chastan,W.Szurhaj,C.Mar chal,H.Catenoix,L.Valton,M.Gavaret,B.Herlin, andA.Biraben,(2023)“Earlyidentificationofseizure freedomwithmedicaltreatmentinpatientswithmesial temporallobeepilepsyandhippocampalsclerosis"Jour nalofNeurology270:2715–2723.DOI: https://doi.org/10.1007/s00415-023-11603-7.
[4] P.Kerezoudis,I.N.Tsayem,B.N.Lundstrom,and J.J.V.Gompel,(2022)“Systematicreviewandpatient levelmeta-analysisofradiofrequencyablationformedi callyrefractoryepilepsy: Implications forclinicalprac ticeandresearch"Seizure102:113–119.DOI: https://doi.org/10.1016/j.seizure.2022.10.003.
[5] X.Kong, J.Luo,andX.Feng, (2024)“AnOverview ofConventionalMSPCMethods"ProcessMonitoring andFaultDiagnosisBasedonMultivariableStatis ticalAnalysis:9–25.DOI: https://doi.org/10.1007/978-981-99-8775-7_2.
[6] K.Fujiwara,K.Ota,S.Saeda,T.Yamakawa,T.Kubo, A.Yamamoto,Y.Maruno,andM.Kano,(2024)“Heat illnessdetectionwithheartratevariabilityanalysisand anomalydetectionalgorithm"BiomedicalSignalPro cessingandControl87:105520. DOI: https://doi.org/10.1016/j.bspc.2023.105520.
[7] Z.Mati´c,A.Kalauzi,M.Platiša,andT.Boji´c.“Sen sitivityEstimationsinFavorofUsingInter-fractal AngleinDetrendedFluctuationAnalysis”.In:IEEE, 2022,1–2.DOI:10.1109/ESGCO55423.2022.9931387.
[8] P.Kumar,A.K.Das,V.Ranjan,andS.Halder.“Frac talCorrelationofHRVforPosturalChangeinYoung MalesandFemales”. In: IEEE,2022,1–5.DOI:10.1109/MysuruCon55714.2022.9972604.
[9] B. Rogers, M. Schaffarczyk, M. Clauß, L. Mourot, and T. Gronwald, (2022) “The movesense medical sen sor chest belt device as single channel ECG for RR interval detection and HRV analysis during resting state and in cremental exercise: A cross-sectional validation study" Sensors 22: 2032. DOI: https://doi.org/10.3390/s22052032.
[10] R. Nomura and T. Yoshida, (2022) “A Missing RR Interval Complement Method Based on Respiratory Fea tures" Advanced Biomedical Engineering 11: 237 248. DOI: https://doi.org/10.14326/abe.11.237.
[11] T. Ouypornkochagorn, (2019) “Misinterpretation of scalp voltage response in the application of electrical impedance tomography to the head" Journal of Applied Science and Engineering 22: 501–508. DOI: https://doi.org/10.6180/jase.201909_22(3).0011.
[12] N.Mahmoudi,M.K.Moridani, M. Khosroshahi, and S. T. Moghadam. Epileptic seizure prediction using ge ometrical features extracted from HRV signal. Springer, 2022, 487–500. DOI: 10.1007/978-981-16-9605-3_33
[13] R. Pernice, L. Faes, M. Feucht, F. Benninger, S. Man gione, and K. Schiecke, (2022) “Pairwise and higher order measures of brain-heart interactions in children with temporal lobe epilepsy" Journal of Neural Engineering 19: 045002. DOI: 10.1088/1741-2552/ac7fba.
[14] D. Zambrana-Vinaroz, J. M. Vicente-Samper, J. Manrique-Cordoba, and J. M. Sabater-Navarro, (2022) “Wearable epileptic seizure Prediction System based on machine learning techniques using ECG, PPG and EEG signals" Sensors 22: 9372. DOI: https://doi.org/10.3390/s22239372.
[15] P. Yushkevich, Y. Gao, and G. Gerig. 2016 38th an nual international conference of the IEEE engineering in medicine and biology society (EMBC). 2016. DOI: 10.1109/EMBC.2016.7590867.
[16] S. Behbahani, N. J. Dabanloo, A. M. Nasrabadi, G. Attarodi, C. A. Teixeira, and A. Dourado. “Epileptic seizure behaviour from the perspective of heart rate variability”. In: 2012 Computing in Cardiology. IEEE, 2012, 117–120. DOI: 10.13140/RG.2.2.14051.81448.
[17] K. R. dos Santos, M. A. de Abreu de Sousa, S. D. dos Santos, R. Pires, and S. Thome-Souza, (2022) “Dif ferentiation between epileptic and psychogenic nonepilep tic seizures in electroencephalogram using wavelets and support-vector machines" Applied Artificial Intelli gence 36: 2008612. DOI: https://doi.org/10.1080/08839514.2021.2008612.
[18] A.M.Anter,M.A.Elaziz,andZ.Zhang,(2022) “Real time epileptic seizure recognition using Bayesian genetic whale optimizer and adaptive machine learning" Future Generation Computer Systems 127: 426–434. DOI: https://doi.org/10.1016/j.future.2021.09.032.
[19] Y. Zhang, Y. Guo, P. Yang, W. Chen, and B. Lo, (2019) “Epilepsy seizure prediction on EEG using common spatial pattern and convolutional neural network" IEEE Journal of Biomedical and Health Informatics 24: 465–474. DOI: 10.1109/JBHI.2019.2933046.
[20] C. Ufongene, R. E. Atrache, T. Loddenkemper, and C. Meisel, (2020) “Electrocardiographic changes asso ciated with epilepsy beyond heart rate and their utiliza tion in future seizure detection and forecasting methods" Clinical Neurophysiology 131: 866–879. DOI: https://doi.org/10.1016/j.clinph.2020.01.007.
[21] D. Nabil, R. Benali, and F. B. Reguig, (2020) “Epilep tic seizure recognition using EEG wavelet decomposi tion based on nonlinear and statistical features with sup port vector machine classification" Biomedical Engi neering/Biomedizinische Technik 65: 133–148. DOI: https://doi.org/10.1515/bmt-2018-0246.
[22] S. Huang, (2021) “Analysis of psychological teaching as sisted by artificial intelligence in sports training courses" Journal of Applied Science and Engineering 24: 743–748. DOI: https://doi.org/10.6180/jase.202110_24(5).0008.
[23] A. S. Zandi, R. Tafreshi, M. Javidan, and G. A. Du mont, (2013) “Predicting epileptic seizures in scalp EEG based on avariational Bayesian Gaussian mixture model of zero-crossing intervals" IEEE Transactions on Biomed ical Engineering 60: 1401–1413. DOI: 10.1109/TBME.2012.2237399.