New AI system can predict seizures with near-perfect accuracy

The system requires to be trained on each patient with few hours of non-invasive EEG monitoring around and during the time of a seizure.

Update: 2019-11-17 04:35 GMT
The new AI system, developed by Hisham Daoud and Magdy Bayoumi of the University of Louisiana at Lafayette, trains on the electroencephalogram (EEG) data of the patient.

Researchers have developed a new AI system that is capable of predicting epileptic seizures up to one hour before they occur.

As IEEE Spectrum notes, the new AI system, developed by Hisham Daoud and Magdy Bayoumi of the University of Louisiana at Lafayette, trains on the electroencephalogram (EEG) data of the patient to accurately predict the occurrence of seizures up to one hour before onset with 99.6 per cent accuracy.

For precision, the system requires to be trained on each patient with few hours of non-invasive EEG monitoring around and during the time of a seizure. Once improved, the system could provide patients with time to prepare for the occurrence and take medication.

Tags:    

Similar News