Autonomic nervous system changes detected with peripheral sensors in the setting of epileptic seizures

Abstract

A better understanding of the early detection of seizures is highly desirable as identification of an impending seizure may afford improved treatments, such as antiepileptic drug chronotherapy, or timely warning to patients. While epileptic seizures are known to often manifest also with autonomic nervous system (ANS) changes, it is not clear whether ANS markers, if recorded from a wearable device, are also informative about an impending seizure with statistically significant sensitivity and specificity. Using statistical testing with seizure surrogate data and a unique dataset of continuously recorded multi-day wristband data including electrodermal activity (EDA), temperature (TEMP) and heart rate (HR) from 66 people with epilepsy (9.9 ± 5.8 years; 27 females; 161 seizures) we investigated differences between inter-and preictal periods in terms of mean, variance, and entropy of these signals. We found that signal mean and variance do not differentiate between inter-and preictal periods in a statistically meaningful way. EDA signal entropy was found to be increased prior to seizures in a small subset of patients. Findings may provide novel insights into the pathophysiology of epileptic seizures with respect to ANS function, and, while further validation and investigation of potential causes of the observed changes are needed, indicate that epilepsy-related state changes may be detectable using peripheral wearable devices. Detection of such changes with wearable devices may be more feasible for everyday monitoring than utilizing an electroencephalogram. The current inability to assess when a seizure is most likely to occur constitutes a major burden for people with epilepsy (PWE) 1. From a clinical perspective, this inability precludes the development of better treatments, such as antiepileptic drug chronotherapy adapted to personalized risk profiles, or timely, closed-loop intervention strategies to acutely avert impending seizures 2. Hence, a better understanding of the informative biomarkers underlying the transition to seizures is needed. Most research devoted to the study of seizure onset mechanisms and prior warning signals has traditionally focused on electroencephalogram (EEG). Continuous EEG, however, is impractical for monitoring over extended periods of time, especially when used in the ambulatory setting 3. Wearable devices might offer a promising alternative, as these afford easy-to-use, close monitoring of autonomic nervous system (ANS) function without being invasive or restraining to PWE 4. Alterations of ANS activity are known to occur frequently within multiple domains, such as electrodermal, thermal and cardiac subsystems, in relation to seizures, and show specific patterns across these parameters 5-7. However, further research on these subsystems of the ANS and whether they may afford statistically meaningful identification of preictal periods in terms of sensitivity and specificity is needed.

Machine learning from wristband sensor data for wearable, noninvasive seizure forecasting

“…Our results demonstrate that there exists a preictal signature in autonomous nervous system 30 and actigraphy data, which, despite possibly not being detectable by visual inspection, may be picked up by deep learning. Importantly, our work demonstrates that this signature may be learned across patients and is therefore not patient-specific.…”

Seizure detection using wearable sensors and machine learning: Setting a benchmark

“…Monitoring of such physiologic signals may allow for tracking of seizure‐related autonomic changes and seizure detection, and ultimately also provide information regarding sudden unexpected death in epilepsy (SUDEP) risk and seizure severity 41 . In particular, multimodal signal analysis has shown promise in this area 43–47 . Findings may also complement the detection of nonconvulsive seizures, which are harder to monitor and detect with non‐EEG devices 8 …”

“… 41 In particular, multimodal signal analysis has shown promise in this area. 43 , 44 , 45 , 46 , 47 Findings may also complement the detection of nonconvulsive seizures, which are harder to monitor and detect with non‐EEG devices. 8 …”

Is There a Characteristic Autonomic Response During Outbursts of Combative Behavior in Dementia Patients?

“…Many studies have demonstrated that seizures are associated with increased heart rate and skin conductance [19][20][21][22][23][24][25][26][27]. In particular, heart rate and skin conductance may distinguish between epileptic seizures (ES) and psychogenic non-epileptic seizures (PNES) [26].…”