In 2007, the research team at MIT Media Lab led by Prof. Rosalind Picard, Empatica’s Chief Scientist, developed a wearable that measured autonomic activity. While trying to help people with autism be better understood, Picard’s team found an unusually high response from one participant. It turned out to be a seizure.
This led to new investigations with Boston Children’s Hospital. With data from over 90 patients, the team learned they had built a more accurate method for seizure monitoring.
Their research was published in top peer-reviewed medical and engineering journals, such as Epilepsia. The research paper, Poh et al 2012a demonstrated the benefit of using electrodermal activity (EDA) together with motion to detect generalized tonic-clonic seizures. Patents were issued, and a version of their sensor was then used in hundreds of top labs, universities, and hospitals.
In one of the published studies (Poh et al. 2012b), the vast majority of complex partial seizures in a group of children caused a significantly large autonomic response. This work has been replicated in adults (Ramgopal S et al. 2014) as well, however, their autonomic responses tended to be milder.
Since Poh's study, researchers at Empatica are constantly improving the algorithm for seizure classification. Their work leads to the following contributions: Onorati, F., Regalia G. (2017) and Onorati et al. 2018.
The published results cited above were from predicate devices. To view recent findings using Embrace please see: Event detection accuracy