Three Biosignals More Accurately Detect Seizures Than Heart Rate Alone

Furthermore, 2 complex partial seizures (CPS) showed less pronounced SpO2 disturbances, which the researchers plan to capture via more advanced, wavelet-based signal processing, while only 2 CPS demonstrated undisturbed SpO2.

According to Cogan, prior to the study, investigators had hoped that patients’ seizures would cause sufficient changes in the signals to allow for improved accuracy of extracerebral seizure detection.

“Based on the results of our first study … we expect to realize this goal,” she said. “What we were pleasantly surprised to find was that 3 of these signals — [HR], [SpO2] and [EDA] — not only changed in response [to] seizures for most of the patients in our study, but also created a specific pattern. We created a time series analysis/pattern recognition-based algorithm …  that allows us to detect nonconvulsive as well as convulsive seizures with very high accuracy in 8 out of 11 patients.”

Going forward, Cogan said that long-term research goals for the study group include: developing a wrist-worn system that detects seizures, alerts a caregiver, and provides feedback to the patient; creating an electronic diary for use by physicians; and creating a database of biosignal response to seizures that aids research into the causes and warning signs of sudden unexpected death in patients with epilepsy.

For more coverage of AES 2015, go here.

Reference

  1. Cogan DL, Nourani M, Harvey J, Nagaraddi V. Abstract 3.084. Seizure detection by multi extracerebral biosignal analysis. Presented at: American Epilepsy Society Annual Meeting; Dec. 4-8, 2015; Philadelphia.