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

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

Sensors (Basel). 2022 Dec 1;22(23):9372. doi: 10.3390/s22239372.

Authors

David Zambrana-Vinaroz¹, Jose Maria Vicente-Samper¹, Juliana Manrique-Cordoba¹, Jose Maria Sabater-Navarro¹

Affiliation

¹ Neuroengineering Biomedical Research Group, Miguel Hernández University of Elche, 03202 Elche, Spain.

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.

Keywords: ECG; HRV; PPG; PTT; ear EEG; epilepsy; machine learning; outdoors seizure prediction; wearable.

MeSH terms

Electroencephalography* / methods
Epilepsy* / diagnosis
Humans
Machine Learning
Quality of Life
Seizures / diagnosis

Grants and funding

The authors would like to thank the neurology team of the Hospital Vega Baja for their collaboration and the work they carry out. The work of D.Z.-V. was funded by Conselleria de Innovación, Universidades, Ciencia y Sociedad Digital and European Social Fund through the ACIF predoctoral program, grant number ACIF/2019/058. The work of J.M.V.-S. is supported by the Conselleria d’Educaci ´o, Investigacio ´, Cultura i Esport (GVA) through FDGENT/2018/015 project.