From Wearables to THINKables: Managing and Treating Epilepsy using AI       


Stefan Harrer photo Isabell Kiral-Kornek photo

From Wearables to THINKables: Managing and Treating Epilepsy using AI - overview

Using brain-inspired chips and deep learning for epilepsy treatment

Epilepsy is the most common, chronic non-communicable disorder of the brain that affects people of all ages. Approximately 50 million individuals worldwide suffer of this disease. 

People with epilepsy often live in fear and uncertainty about when a seizure is going to occur, with one third of patients completely unreceptive to any sort of treatment through medication. At IBM Research – Australia, we follow novel AI approaches to develop personalised medicine techniques for monitoring epileptic seizure activity and predicting seizures before they strike.

We are using deep learning, neuromorphic hardware and long-term brain activity data to develop an automated, mobile, patient-tunable epileptic seizure prediction system.

Our scientists envision an intelligent, wearable device which may identify signs of an upcoming seizure and alert a patient or automatically administer medication. This could not only dramatically improve the lives of people with epilepsy, but save lives too.

More about Brain-Inspired Computing Research

New research in AI pushes frontiers in epileptic seizure prediction

Epileptic Seizure Prediction Using Big Data and Deep Learning: Toward a Mobile System