Nathan Intrator on epilepsy, AI, and digital signal processing | ApplySci @ Stanford

Nathan Intrator discussed epilepsy, AI and digital signal processing at ApplySci’s Wearable Tech + Digital Health + Neurotech Silicon Valley conference on February 26-27, 2018 at Stanford University:

Join ApplySci at the 9th Wearable Tech + Digital Health + Neurotech Boston conference on September 24, 2018 at the MIT Media Lab.  Speakers include:  Mary Lou Jepsen – George ChurchRoz PicardNathan IntratorKeith JohnsonJuan EnriquezJohn MattisonRoozbeh GhaffariPoppy Crum

Video: Roz Picard on wrist-sensed stress, seizure & brain data

Recorded at ApplySci’s Wearable Tech + Digital Health + Neurotech Boston conference on September 19th at the MIT Media Lab

Join ApplySci at Wearable Tech + Digital Health + Neurotech Silicon Valley on February 26-27, 2018 at Stanford University. Speakers include:  Vinod Khosla – Justin Sanchez – Brian Otis – Bryan Johnson – Zhenan Bao – Nathan Intrator – Carla Pugh – Jamshid Ghajar – Mark Kendall – Robert Greenberg – Darin Okuda – Jason Heikenfeld – Bob Knight – Phillip Alvelda – Paul Nuyujukian –  Peter Fischer – Tony Chahine – Shahin Farshchi – Ambar Bhattacharyya – Adam D’Augelli – Juan-Pablo Mas – Michael Eggleston

Registration rates increase today, December 1st

App detects seizure onset with heart rate, accelerometer data

Johns Hopkins professor Gregory Krauss has used ResearchKit to develop an app to detect the onset and duration of epileptic seizures with an Apple Watch.  Wearers must touch the watch to capture accelerometer and heart rate sensor data, and notify a caregiver.  The EpiWatch app logs seizures and responses, and tracks medication adherence and side effects.

The EpiWatch is similar in function to Embrace by Empatica, developed by MIT professor Rosalind Picard.  Embrace uses skin conductance, accelerator, and gyrometer  data to detect seizures.  (See ApplySci, November 28, 2014.)

ApplySci applauds these advances, which by recording patterns and notifying loved ones,  have the potential to improve the lives of epilepsy sufferers.  There is little evidence that cardiac activity alone can be used to predict seizures (see Amir Geva‘s paper in IEEE Transactions on Biomedical Engineering).  The next step is to develop the ability to predict seizures in advance, which will require brain activity interpretation.



Epileptic patients process music differently

Ohio State researchers have found that epileptic patients’ brains process music differently, and hypothesize that music therapy could be used to reduce temporal lobe seizure frequency.

The brainwaves of 21  epileptic and healthy patients were examined as they listened to music, interspersed with moments of silence. The order of the pieces was randomized, and 10 minutes of silence preceded and followed each composition.

Subject brainwave activity increased as they listened to music. Epileptic patient brainwaves were even more synchronized with the music.

Christine Charyton presented the research at a recent APA conference, and summarized: “We found significantly higher levels of synchronization and spectral EEG activation when listening to music in the frontal cortex and temporal cortex, especially in persons with epilepsy. We speculate that music may be useful to enhance electrical activity specific to the frontal and temporal cortices,”


Skin conductance based wearable detects seizures

Embrace by Empatica is a sleek, crowdfunded wearable that detects epileptic seizures.  It also tracks movement, sleep, and stress.  The technology is based on Rosalind Picard‘s 2008 study showing that seizures produce high levels of skin conductance.

Other seizure logging wearables focus on accelerometer tracked motion.  Empatica believes that Embrace more accurately measures seizures by combining accelerometer and gyroscope data with skin conductance measurements.  Electrodes on the inside of Embrace pass a tiny current through one’s skin to measure sweat gland stimulation.

The band vibrates if the algorithm detects a seizure, enabling the user to indicate a false alarm. If the user doesn’t respond, Embrace connect with his or her smartphone to alert designated contacts.

Transparent brain implant could improve neuromodulation

University of Wisconsin professor Justin Williams and colleagues have developed a graphene based, transparent sensor implant to help researchers better view the brain.  Unlike existing devices, the sensor’s micro electrode arrays work in tandem with imaging technologies.  This could improve neuromodulation therapies used to control symptoms, restore function, and relieve pain in patients with hypertension, epilepsy, or Parkinson’s.  Researchers have been limited in their ability to directly observe how the body generates electrical signals, or how it reacts to externally generated electrical signals.  According to Williams, “Clear electrodes in combination with recent technological advances in optogenetics and optical voltage probes will enable researchers to isolate those biological mechanisms. This fundamental knowledge could be catalytic in dramatically improving existing neuromodulation therapies and identifying new therapies.”


DARPA neuromodulation tech for physical and mental health

DARPA‘s ElectRx research program aims to develop high precision, minimally-invasive neuromodulation technologies to treat diseases including rheumatoid arthritis, epilepsy and PTSD.

Implanted ultraminiaturized devices would modulate the peripheral nervous system’s response to infections, injuries or other imbalances.

Project manager Doug Weber claims that ElectRX technologies “would continually assess conditions and provide stimulus patterns tailored to help maintain healthy organ function, helping patients get healthy and stay healthy using their body’s own systems.”


Wearables track, manage, predict epileptic seizures

Artefact Dialog | SmartMonitor

Artefact Dialog allows epilepsy patients to track, manage, and predict seizures.

The patch-like wearable connects via Bluetooth to a smartphone app.  It can help wearers remember to take their medications, warn them about seizures, and alert friends, family, or caregivers when a seizure happens. Connected apps help users analyze where they have been and what they were doing when seizures occurred, and instruct bystanders and responders what to do during an episode.

Featuring a UI based around natural interactions, Dialog allows patients to call for help with a grasp of the patch. A double tap allows a patient to record a pre-seizure aura, and can measure the typical time between an aura and a seizure. Tracing a smile or frown lets wearers track their moods, and vibrations alert users to take their medications.

Last year SmartMonitor released its epilepsy focused smart watch, with similar features but a more traditional design.