Validation of Continuous Monitoring System for Epileptic Users in Outpatient Settings

Abstract

Epilepsy is a chronic disease with a significant social impact, given that the patients and their families often live conditioned by the possibility of an epileptic seizure and its possible consequences, such as accidents, injuries, or even sudden unexplained death. In this context, ambulatory monitoring allows the collection of biomedical data about the patients’ health, thus gaining more knowledge about the physiological state and daily activities of each patient in a more personalized manner. For this reason, this article proposes a novel monitoring system composed of different sensors capable of synchronously recording electrocardiogram (ECG), photoplethysmogram (PPG), and ear electroencephalogram (EEG) signals and storing them for further processing and analysis in a microSD card. This system can be used in a static and/or ambulatory way, providing information about the health state through features extracted from the ear EEG signal and the calculation of the heart rate variability (HRV) and pulse travel time (PTT). The different applied processing techniques to improve the quality of these signals are described in this work. A novel algorithm used to compute HRV and PTT robustly and accurately in ambulatory settings is also described. The developed device has also been validated and compared with other commercial systems obtaining similar results. In this way, based on the quality of the obtained signals and the low variability of the computed parameters, even in ambulatory conditions, the developed device can potentially serve as a support tool for clinical decision-taking stages.

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

“…For the acquisition of the signals studied, a novel monitoring system was developed consisting of different sensors capable of synchronously recording at 250 Hz the electrocardiogram (ECG), photoplethysmogram (PPG) and 3 electroencephalogram (EEG) channels of the ear and storing them for further processing and analysis on a microSD card. Such a system has been extensively described in [ 29 ]. This device provides information on health status through the calculation of heart rate variability (HRV), pulse travel time (PTT) and certain characteristics of the ear EEG signal.…”

“…For each of the three ear EEG signals obtained, a bandpass filter from 0.5 Hz to 40 Hz was used. These filtering techniques are extensively discussed in [ 29 ].…”

“…The HRV parameter is obtained directly from the ECG signal by calculating the time between the R peaks. However, to calculate the PTT parameter, it is necessary to measure the time between the R peak of the ECG signal and the next peak of the PPG signal as indicated in [ 29 , 31 ]. Figure 4 shows the variation in milliseconds of the HRV and PTT values of a volunteer throughout the experimental procedure (40 min).…”

“…After an extensive literature review, no devices have been found that simultaneously measure ECG, PPG and ear-EEG. Consequently, a device [ 29 ] capable of recording these signals has been used with epileptic patients in a clinical environment. By processing these data and using supervised machine learning techniques, different predictive models have been developed, which are capable of classifying the state of the epileptic person into normal, pre-seizure and seizure.…”

Heart Rate Variability as a Tool for Seizure Prediction: A Scoping Review

“…A total of N = 9 papers were reviewed analyzing seizure detection systems built with wearable devices, facing challenges related to the online estimation of HRV. Three studies analyzed systems to extract heartbeats in people with epilepsy automatically, without providing results in terms of detection accuracy [106][107][108]. In three consecutive studies, Jeppesen designed and refined a wearable system for detecting seizures during the activities of daily living [91, 105,109].…”