Wearable Epileptic Seizure Prediction System Based on Machine Learning Techniques Using ECG, PPG and EEG Signals

David Zambrana-Vinaroz; Jose Maria Vicente-Samper; Juliana Manrique-Cordoba; Jose Maria Sabater-Navarro

doi:10.3390/s22239372

journal article Open Access Dec 01, 2022

Wearable Epileptic Seizure Prediction System Based on Machine Learning Techniques Using ECG, PPG and EEG Signals

David Zambrana-Vinaroz

Jose Maria Vicente-Samper

Juliana Manrique-Cordoba

Jose Maria Sabater-Navarro

Sensors Vol. 22 No. 23 pp. 9372 · MDPI AG

View at Publisher Save 10.3390/s22239372

Abstract

Epileptic seizures have a great impact on the quality of life of people who suffer from them and further limit their independence. For this reason, a device that would be able to monitor patients’ health status and warn them for a possible epileptic seizure would improve their quality of life. With this aim, this article proposes the first seizure predictive model based on Ear EEG, ECG and PPG signals obtained by means of a device that can be used in a static and outpatient setting. This device has been tested with epileptic people in a clinical environment. By processing these data and using supervised machine learning techniques, different predictive models capable of classifying the state of the epileptic person into normal, pre-seizure and seizure have been developed. Subsequently, a reduced model based on Boosted Trees has been validated, obtaining a prediction accuracy of 91.5% and a sensitivity of 85.4%. Thus, based on the accuracy of the predictive model obtained, it can potentially serve as a support tool to determine the status epilepticus and prevent a seizure, thereby improving the quality of life of these people.

Topics

No keywords indexed for this article. Browse by subject →

References

51

[1]

(2022, June 30). Epilepsy. Available online: https://www.who.int/news-room/fact-sheets/detail/epilepsy.

[2]

Fisher "How can we identify ictal and interictal abnormal activity?" Adv. Exp. Med. Biol. (2014) 10.1007/978-94-017-8914-1_1

[3]

Nijsen "The potential value of three-dimensional accelerometry for detection of motor seizures in severe epilepsy" Epilepsy Behav. (2005) 10.1016/j.yebeh.2005.04.011

[4]

Heldberg, B.E., and Kautz, T. (2015, January 25–29). Wearable sensors for semiology-independent seizure detection—Towards ambulatory monitoring of epilepsy. Proceedings of the 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Milan, Italy. 10.1109/embc.2015.7319660

[5]

Tzallas "Epileptic Seizure Detection in EEGs Using Time–Frequency Analysis" IEEE Trans. Inf. Technol. Biomed. (2009) 10.1109/titb.2009.2017939

[6]

Acharya "Automated EEG analysis of epilepsy: A review" Knowl.-Based Syst. (2013) 10.1016/j.knosys.2013.02.014

[7]

You "Unsupervised automatic seizure detection for focal-onset seizures recorded with behind-the-ear EEG using an anomaly-detecting generative adversarial network" Comput. Methods Programs Biomed. (2020) 10.1016/j.cmpb.2020.105472

[8]

Gu, Y., Cleeren, E., Dan, J., Claes, K., Van Paesschen, W., Van Huffel, S., and Hunyadi, B. (2018). Comparison between scalp EEG and behind-the-ear EEG for development of a wearable seizure detection system for patients with focal epilepsy. Sensors, 18. 10.3390/s18010029

[9]

Bleichner "Concealed, Unobtrusive Ear-Centered EEG Acquisition: cEEGrids for Transparent EEG" Front. Hum. Neurosci. (2017) 10.3389/fnhum.2017.00163

[10]

Rafie "ECG Interpretation: Clinical Relevance, Challenges, and Advances" Hearts (2021) 10.3390/hearts2040039

[11]

Uijtdehaage "Accentuated antagonism in the control of human heart rate" Clin. Auton. Res. (2000) 10.1007/bf02278013

[12]

Massin "Circadian rhythm of heart rate and heart rate variability" Arch. Dis. Child (2000) 10.1136/adc.83.2.179

[13]

Myers "Heart rate variability in epilepsy: A potential biomarker of sudden unexpected death in epilepsy risk" Epilepsia (2018) 10.1111/epi.14438

[14]

Block "Conventional pulse transit times as markers of blood pressure changes in humans" Sci. Rep. (2020) 10.1038/s41598-020-73143-8

[15]

Nass "Blood Pressure in Seizures and Epilepsy" Front. Neurol. (2019) 10.3389/fneur.2019.00501

[16]

(2022, June 30). Post-ictal Physiology: Adding Blood Pressure to the Equation. Available online: https://www.epilepsy.com/article/2016/12/post-ictal-physiology-adding-blood-pressure-equation.

[17]

(2022, June 30). Embrace2®. Available online: https://www.empatica.com/en-eu/embrace2/.

[18]

MJN (2022, June 30). Seras®. Available online: https://mjn.cat/.

[19]

(2022, June 30). EpiWatch®. Available online: https://www.apple.com/es/researchkit/.

[20]

(2022, June 30). SmartWatch by Smart Monitor®. Available online: https://www.epilepsy.com/deviceapedia/smartwatch-smart-monitor-0.

[21]

Patterson "SmartWatch by SmartMonitor: Assessment of seizure detection efficacy for various seizure types in children: A large prospective single-center study" Pediatr. Neurol. (2015) 10.1016/j.pediatrneurol.2015.07.002

[22]

(2022, June 30). EpiCare@Home. Available online: https://www.epicareathome.com/.

[23]

Yamakawa, T., Miyajima, M., Fujiwara, K., Kano, M., Suzuki, Y., Watanabe, Y., Watanabe, S., Hoshida, T., Inaji, M., and Maehara, T. (2020). Wearable Epileptic Seizure Prediction System with Machine-Learning-Based Anomaly Detection of Heart Rate Variability. Sensors, 20. 10.3390/s20143987

[24]

Billeci, L., Tonacci, A., Varanini, M., Detti, P., de Lara, G.Z.M., and Vatti, G. (2019, January 19–21). Epileptic seizures prediction based on the combination of EEG and ECG for the application in a wearable device. Proceedings of the 2019 IEEE 23rd International Symposium on Consumer Technologies (ISCT), Ancona, Italy. 10.1109/isce.2019.8900998

[25]

Nasseri "Non-invasive wearable seizure detection using long-short-term memory networks with transfer learning" J. Neural Eng. (2021) 10.1088/1741-2552/abef8a

[26]

Pavei "Early seizure detection based on cardiac autonomic regulation dynamics" Front. Physiol. (2017) 10.3389/fphys.2017.00765

[27]

Zhou "Epileptic Seizure Detection Based on EEG Signals and CNN" Front Neuroinform. (2018)

[28]

Kusmakar "Automated Detection of Convulsive Seizures Using a Wearable Accelerometer Device" IEEE Trans. Biomed. Eng. (2019) 10.1109/tbme.2018.2845865

[29]

Zambrana-Vinaroz, D., Vicente-Samper, J.M., and Sabater-Navarro, J.M. (2022). Validation of Continuous Monitoring System for Epileptic Users in Outpatient Settings. Sensors, 22. 10.3390/s22082900

[30]

(2022, June 30). EEG Nicolet V32®. Available online: https://neuro.natus.com/es-es/productos-y-servicios/sistema-de-eeg-nicoletone.

[31]

Zambrana-Vinaroz, D., Vicente-Samper, J.M., Juan, C.G., Esteve-Sala, V., and Sabater-Navarro, J.M. (2022). Non-Invasive Device for Blood Pressure Wave Acquisition by Means of Mechanical Transducer. Sensors, 19. 10.3390/s19194311

[32]

Wood "La Hiperventilación y el Trastorno de Angustia a la Luz de un Marco Cognitivo" Clín. Salud. (2021)

[33]

Liu "Epileptic Seizure Classification with Symmetric and Hybrid Bilinear Models" IEEE J. Biomed. Health Inform. (2020) 10.1109/jbhi.2020.2984128

[34]

Albaqami, H., Hassan, G.M., and Datta, A. (2022). Wavelet-Based Multi-Class Seizure Type Classification System. Appl. Sci., 12. 10.2139/ssrn.4040674

[35]

Esco "Ultra-short-term heart rate variability indexes at rest and post-exercise in athletes: Evaluating the agreement with accepted recommendations" J. Sport. Sci. Med. (2014)

[36]

An Overview of Heart Rate Variability Metrics and Norms

Fred Shaffer, J. P. Ginsberg

Frontiers in Public Health 2017 10.3389/fpubh.2017.00258

[37]

DeGiorgio "RMSSD, a measure of vagus-mediated heart rate variability, is associated with risk factors for SUDEP: The SUDEP-7 Inventory" Epilepsy Behav. (2010) 10.1016/j.yebeh.2010.06.011

[38]

Kim "Application and Limitation of Frequency Domain, LF/HF Component in Heart Rate Variability as an Acute Stress Index" Age (2014)

[39]

Heathers "Everything Hertz: Methodological issues in short-term frequency-domain HRV" Front. Physiol. (2014) 10.3389/fphys.2014.00177

[40]

Sánchez-Hernández, S.E., Salido-Ruiz, R.A., Torres-Ramos, S., and Román-Godínez, I. (2022). Evaluation of Feature Selection Methods for Classification of Epileptic Seizure EEG Signals. Sensors, 22. 10.3390/s22083066

[41]

Boonyakitanont "A review of feature extraction and performance evaluation in epileptic seizure detection using EEG" Biomed. Signal Process. Control (2020) 10.1016/j.bspc.2019.101702

[42]

Snyder "The statistics of a practical seizure warning system" J. Neural Eng. (2008) 10.1088/1741-2560/5/4/004

[43]

(2022, June 30). Autoregressive Power Spectral Density Estimate—Burg’s Method. Available online: https://es.mathworks.com/help/signal/ref/pburg.html.

[44]

Zijlmans "Ictal and interictal high frequency oscillations in patients with focal epilepsy" Clin. Neurophysiol. (2011) 10.1016/j.clinph.2010.09.021

[45]

(2022, June 30). Classification Learner App. Available online: https://www.mathworks.com/help/stats/classificationlearner-app.html.

[46]

(2022, June 30). Principal Component Analysis (PCA). Available online: https://www.mathworks.com/help/stats/principal-component-analysis-pca.html.

[47]

Morales, A., Fierrez, J., Sánchez, J.S., and Ribeiro, B. (2019). Addressing the Big Data Multi-class Imbalance Problem with Oversampling and Deep Learning Neural Networks. Pattern Recognition and Image Analysis, Springer International Publishing.

[48]

Browne "Cross-Validation Methods" J. Math. Psychol. (2000) 10.1006/jmps.1999.1279

[49]

(2022, June 30). Neighborhood Component Analysis (NCA) Feature Selection. Available online: https://www.mathworks.com/help/stats/neighborhood-component-analysis.html.

[50]

Billeci, L., Marino, D., Insana, L., Vatti, G., and Varanini, M. (2018). Patient-specific seizure prediction based on heart rate variability and recurrence quantification analysis. PLoS ONE, 13. 10.1371/journal.pone.0204339

Showing 50 of 51 references

Cited By

46

Machine-learning methods for epilepsy diagnosis and therapeutic prevention: advances, setbacks, and opportunities

Nitu L. Wankhede, Saeed Alshahrani · 2026

Neurological Sciences

Artificial Intelligence and Machine Learning in Neuromodulation for Epilepsy

Brian Ervin, Ravindra Arya · 2025

Journal of Clinical Neurophysiology

Innovating pediatric epilepsy: transforming diagnosis and treatment with AI

Giovanni Battista Dell’Isola, Antonella Fattorusso · 2025

World Journal of Pediatrics

Advancing EEG-based brain-computer interface technology via PEDOT:PSS electrodes

Yang Li, Yuzhe Gu · 2024

Matter

Metrics

46

Citations

51

References

Details

Published: Dec 01, 2022
Vol/Issue: 22(23)
Pages: 9372
License: View

Authors

D

David Zambrana-Vinaroz

Neuroengineering Biomedical Research Group, Miguel Hernández University of Elche, 03202 Elche, Spain

J

Jose Maria Vicente-Samper

Neuroengineering Biomedical Research Group, Miguel Hernández University of Elche, 03202 Elche, Spain

J

Juliana Manrique-Cordoba

Neuroengineering Biomedical Research Group, Miguel Hernández University of Elche, 03202 Elche, Spain

J

Jose Maria Sabater-Navarro

Neuroengineering Biomedical Research Group, Miguel Hernández University of Elche, 03202 Elche, Spain

Funding

neurology team of the Hospital Vega Baja Award: ACIF/2019/058

Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital and European Social Fund through the ACIF predoctoral program Award: ACIF/2019/058

Conselleria d’Educaci ́o, Investigacio ́, Cultura i Esport (GVA) Award: ACIF/2019/058

Cite This Article

David Zambrana-Vinaroz, Jose Maria Vicente-Samper, Juliana Manrique-Cordoba, et al. (2022). Wearable Epileptic Seizure Prediction System Based on Machine Learning Techniques Using ECG, PPG and EEG Signals. Sensors, 22(23), 9372. https://doi.org/10.3390/s22239372

Wearable Epileptic Seizure Prediction System Based on Machine Learning Techniques Using ECG, PPG and EEG Signals

You May Also Like