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

OBJECTIVE: Tracking seizures is crucial for epilepsy monitoring and treatment evaluation. Current epilepsy care relies on caretaker seizure diaries, but clinical seizure monitoring may miss seizures. Wearable devices may be better tolerated and more suitable for long-term ambulatory monitoring. This study evaluates the seizure detection performance of custom-developed machine learning (ML) algorithms across a broad spectrum of epileptic seizures utilizing wrist- and ankle-worn multisignal biosensors. METHODS: We enrolled patients admitted to the epilepsy monitoring unit and asked them to wear a wearable sensor on either their wrists or ankles. The sensor recorded body temperature, electrodermal activity, accelerometry (ACC), and photoplethysmography, which provides blood volume pulse (BVP). We used electroencephalographic seizure onset and offset as determined by a board-certified epileptologist as a standard comparison. We trained and validated ML for two different algorithms: Algorithm 1, ML methods for developing seizure type-specific detection models for nine individual seizure types; and Algorithm 2, ML methods for building general seizure type-agnostic detection, lumping together all seizure types. RESULTS: We included 94 patients (57.4% female, median age = 9.9 years) and 548 epileptic seizures (11 066 h of sensor data) for a total of 930 seizures and nine seizure types. Algorithm 1 detected eight of nine seizure types better than chance (area under the receiver operating characteristic curve [AUC-ROC] = .648-.976). Algorithm 2 detected all nine seizure types better than chance (AUC-ROC = .642-.995); a fusion of ACC and BVP modalities achieved the best AUC-ROC (.752) when combining all seizure types together. SIGNIFICANCE: Automatic seizure detection using ML from multimodal wearable sensor data is feasible across a broad spectrum of epileptic seizures. Preliminary results show better than chance seizure detection. The next steps include validation of our results in larger datasets, evaluation of the detection utility tool for additional clinical seizure types, and integration of additional clinical information.

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

OBJECTIVE: Seizure forecasting may provide patients with timely warnings to adapt their daily activities and help clinicians deliver more objective, personalized treatments. Although recent work has convincingly demonstrated that seizure risk assessment is in principle possible, these early approaches relied largely on complex, often invasive setups including intracranial electrocorticography, implanted devices, and multichannel electroencephalography, and required patient-specific adaptation or learning to perform optimally, all of which limit translation to broad clinical application. To facilitate broader adaptation of seizure forecasting in clinical practice, noninvasive, easily applicable techniques that reliably assess seizure risk without much prior tuning are crucial. Wristbands that continuously record physiological parameters, including electrodermal activity, body temperature, blood volume pulse, and actigraphy, may afford monitoring of autonomous nervous system function and movement relevant for such a task, hence minimizing potential complications associated with invasive monitoring and avoiding stigma associated with bulky external monitoring devices on the head. METHODS: Here, we applied deep learning on multimodal wristband sensor data from 69 patients with epilepsy (total duration > 2311 hours, 452 seizures) to assess its capability to forecast seizures in a statistically significant way. RESULTS: Using a leave-one-subject-out cross-validation approach, we identified better-than-chance predictability in 43% of the patients. Time-matched seizure surrogate data analyses indicated forecasting not to be driven simply by time of day or vigilance state. Prediction performance peaked when all sensor modalities were used, and did not differ between generalized and focal seizure types, but generally increased with the size of the training dataset, indicating potential further improvement with larger datasets in the future. SIGNIFICANCE: Collectively, these results show that statistically significant seizure risk assessments are feasible from easy-to-use, noninvasive wearable devices without the need of patient-specific training or parameter optimization.

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

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.