New AI System Detects Rare Epileptic Seizures
USC researchers develop AI technique to identify seizure types, including rare forms of epilepsy, increasing opportunity for early intervention
By integrating multiple sources of information usually overlooked by AI systems, including the positions of EEG electrodes and the brain regions they monitor, the AI can identify patterns or features that indicate a seizure is likely to occur. Photo/iStock.
More than 3.4 million people in the US and 65 million people worldwide have epilepsy, a neurological disorder that affects the nervous system and causes seizures. One in 26 people will develop epilepsy at some point in their lives, and 1 out of 1000 people with epilepsy die from unexpected deaths each year.
Like many conditions, epilepsy treatment starts with early detection. The World Health Organization estimates that 70% of people with epilepsy could live seizure-free if adequately diagnosed and treated.
Over the years, machine learning techniques have been developed to detect and classify seizures from electroencephalography (EEG) signals captured using electrodes on the brain, looking for correlations too intricate for humans to tackle alone.
