Autonomic biosignals, seizure detection, and forecasting.

Wearable devices have attracted significant attention in epilepsy research in recent years for their potential to enhance patient care through improved seizure monitoring and forecasting. This narrative review presents a detailed overview of the current clinical state of the art while addressing how devices that assess autonomic nervous system (ANS) function reflect seizures and central nervous system (CNS) state changes. This includes a description of the interactions between the CNS and the ANS, including physiological and epilepsy-related changes affecting their dynamics. We first discuss technical aspects of measuring autonomic biosignals and considerations for using ANS sensors in clinical practice. We then review recent seizure detection and seizure forecasting studies, highlighting their performance and capability for seizure detection and forecasting using devices measuring ANS biomarkers. Finally, we address the field's challenges and provide an outlook for future developments.

Wearable device assessments of antiseizure medication effects on diurnal patterns of electrodermal activity, heart rate, and heart rate variability.

Patient-generated health data provide a great opportunity for more detailed ambulatory monitoring and more personalized treatments in many diseases. In epilepsy, robust diagnostics applicable to the ambulatory setting are needed as diagnosis and treatment decisions in current clinical practice are primarily reliant on patient self-reports, which are often inaccurate. Recent work using wearable devices has focused on methods to detect and forecast epileptic seizures. Whether wearable device signals may also contain information about the effect of antiseizure medications (ASMs), which may ultimately help to better monitor their efficacy, has not been evaluated yet. Here we systematically investigated the effect of ASMs on different data modalities (electrodermal activity, EDA, heart rate, HR, and heart rate variability, HRV) simultaneously recorded by a wearable device in 48 patients with epilepsy over several days in the epilepsy long-term monitoring unit at a tertiary hospital. All signals exhibited characteristic diurnal variations. HRV, but not HR or EDA-based metrics, were reduced by ASMs. By assessing multiple signals related to the autonomic nervous system simultaneously, our results provide novel insights into the effects of ASMs on the sympathetic and parasympathetic interplay in the setting of epilepsy and indicate the potential of easy-to-wear wearable devices for monitoring ASM action. Future work using longer data may investigate these metrics on multidien cycles and their utility for detecting seizures, assessing seizure risk, or informing treatment interventions.

Explainable AI for wearable seizure logging: Impact of data quality, patient age, and antiseizure medication on performance.

OBJECTIVE: Objective seizure count estimates are crucial for ambulatory epilepsy management. Wearables have shown promise for the detection of tonic-clonic seizures but may suffer from false alarms and undetected seizures. Seizure signatures recorded by wearables often occur over prolonged periods, including increased levels of electrodermal activity and heart rate long after seizure EEG onset, however, previous detection methods only partially exploited these signatures. Understanding the utility of these prolonged signatures for seizure count estimation and what factors generally determine seizure logging performance, including the role of data quality vs. algorithm performance, is thus crucial for improving wearables-based epilepsy monitoring and determining which patients benefit most from this technology. METHODS: In this retrospective study we examined 76 pediatric epilepsy patients during multiday video-EEG monitoring equipped with a wearable (Empatica E4; records of electrodermal activity, EDA, accelerometry, ACC, heart rate, HR; 1983 h total recording time; 45 tonic-clonic seizures). To log seizures on prolonged data trends, we applied deep learning on continuous overlapping 1-hour segments of multimodal data in a leave-one-subject-out approach. We systematically examined factors influencing logging performance, including patient age, antiseizure medication (ASM) load, seizure type and duration, and data artifacts. To gain insights into algorithm function and feature importance we applied Uniform Manifold Approximation and Projection (UMAP, to represent the separability of learned features) and SHapley Additive exPlanations (SHAP, to represent the most informative data signatures). RESULTS: Performance for tonic-clonic seizure logging increased systematically with patient age (AUC 0.61 for patients 〈 11 years, AUC 0.77 for patients between 11-15 years, AUC 0.85 for patients 〉 15 years). Across all ages, AUC was 0.75 corresponding to a sensitivity of 0.52 and a false alarm rate of 0.28/24 h. Seizures under high ASM load or with shorter duration were detected worse (P=.025, P=.033, respectively). UMAP visualized discriminatory power at the individual patient level, SHAP analyses identified clonic motor activity and peri/postictal increases in HR and EDA as most informative. In contrast, in missed seizures, these features were absent indicating that recording quality but not the algorithm caused the low sensitivity in these patients. SIGNIFICANCE: Our results demonstrate the utility of prolonged, postictal data segments for seizure logging, contribute to algorithm explainability and point to influencing factors, including high ASM dose and short seizure duration. Collectively, these results may help to identify patients who particularly benefit from such technology.