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

Abstract

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.

Ambulatory seizure forecasting with a wrist-worn device using long-short term memory deep learning

“…The algorithm was trained on 60-s data segments selected from each recording. To ensure the algorithm was performing seizure forecasting rather than early seizure detection, and to account for potential misalignment between the clocks in the wearable and implanted devices and the potential inexact timing of the seizure onset recorded by the device 26 , 27 , one-hour preictal data epochs were defined with a set-back of 15 min before the seizure onset recorded by the implanted EEG device. Lead seizures were defined as seizures separated from preceding seizures by at least 4 h, and clustered (i.e., non-lead) seizures were excluded from analysis to avoid artificially inflating results.…”

Prospective Study of a Multimodal Convulsive Seizure Detection Wearable System on Pediatric and Adult Patients in the Epilepsy Monitoring Unit

“…At present, a clear evidence gap has still to be filled before introducing the automated ambulatory detection of nonconvulsive seizures into clinical practice (28,78,79). However, promising results using the E4 wristband indicated that this may be possible with a wrist-worn device (80)(81)(82). Additionally, advanced post-processing analytics on the peri-ictal periods may provide seizure semiology information, thereby expanding the quality of available patient data.…”

Electrodermal activity response during seizures: A systematic review and meta-analysis

“…Of the included studies, six were included for meta-analysis [17,18,[25][26][27][28]. The remaining 13 studies [19,20,[29][30][31][32][33][34][35][36][37][38][39] were only considered for qualitative analysis, as they did not report the frequency of seizures with an EDA response.…”

“…The nineteen studies included a total of 550 participants (46% male, 44% female, 10% not recorded), and 1115 recorded seizures. Five studies [28,31,37,40,41] included both adult and pediatric populations, four [19,26,27,29] included only adults, with another six [17,18,20,34,38,39] including only children or young adults. Four studies [30,32,33,35] did not report the age of participants.…”

“…Six studies [18,28,31,[37][38][39] included a mixture of genetic and structural/metabolic epilepsies and one study [19] included temporal lobe epilepsies. The remaining twelve studies [17,20,25-27, 29,30,32-35,41] did not report the epilepsy type.…”