Epilepsy

Seizure detection using wearable devices

There is need for automated seizure detection using wearable devices, to decrease the morbidity and mortality associated with seizures, especially with generalized tonic-clonic seizures (GTCS) and to provide objective data on seizure-occurrence, because more than half of the seizures remain unreported.

There is need for automated seizure detection using wearable devices, to decrease the morbidity and mortality associated with seizures, especially with generalized tonic-clonic seizures (GTCS) and to provide objective data on seizure-occurrence, because more than half of the seizures remain unreported. A recently published systematic review (1) of the level of evidence for the available seizure detection devices concluded that automated detection of GTCS using wearable devices was reliable. There are several, validated devices on the market, with approval for medical use. Sixteen studies of phase-2 or above, demonstrated that wearable devices detected GTCS with high sensitivity (≥90%) and low false alarm rate (down to 0.2 false alarms per day). These devices analyzed signals from accelerometers, surface electromyography (EMG) or were based on multimodal signal processing, combining accelerometry with electrodermal activity, EMG, ECG / heart rate. However, detection of other seizure types (including focal seizures with and without impaired awareness) needs further research. For these seizure types there are promising results using signals recorded from implanted EEG electrodes (2) or using changes in the autonomic nervous system.

Key points:

  • Seizure detection
  • epilepsy
  • wearable devices

References:

 

1) Beniczky S, Jeppesen J. Non-electroencephalography-based seizure detection. Curr Opin Neurol. 2019;32:198-204. doi: 10.1097/WCO.0000000000000658.

2) Baldassano SN, Brinkmann BH, Ung H, Blevins T, Conrad EC, Leyde K, Cook MJ, Khambhati AN, Wagenaar JB, Worrell GA, Litt B. Crowdsourcing seizure detection: algorithm development and validation on human implanted device recordings. Brain. 2017;140:1680-1691. doi: 10.1093/brain/awx098