Scientists have developed a new AI-based system which can predict epileptic seizures with 99.6-percent accuracy. It can even predict Seizures up to an hour before they occur.
The new AI-based system is developed by Hisham Daoud and Magdy Bayoumi of the University of Louisiana at Lafayette. The algorithm combines EEG (electroencephalogram) technology with predictive modeling. Earlier models were designed to use the two-stage process. They tested their system on 22 patients at the Boston Children’s Hospital. Tand found a 99.6% accuracy rate with 0.004 false alarms per hour.
However, the system needs to be trained in individual patients. “In order to achieve this high accuracy with early prediction time, we need to train the model on each patient,” says, Daoud.
Daoud says they are now working on a custom chip that can help to process the necessary algorithms. “We are currently working on the design of efficient hardware [device] that deploys this algorithm, considering many issues like system size, power consumption, and latency to be suitable for practical application in a comfortable way to the patient,” he says.