Penn Medicine: Competition Seeks Experts in Science and Machine Learning to Predict and Detect Seizures

facebook twitter google print email
Media Contact:Lee-Ann Donegan | leeann.donegan@uphs.upenn.edu | 215-349-5660July 28, 2014

Epilepsy affects more than 50 million people worldwide. The disorder is caused by abnormal electrical activity in the brain that can bring about seizures, changes in awareness or sensation and behavior. Despite multiple attempts to control seizure activity with medication, three million Americans suffer from recurrent, spontaneous epileptic seizures, the onset of which cannot be predicted or detected in advance.

A team of researchers from Penn and the Mayo Clinic has challenged the best minds in science and “machine learning” to improve devices to treat epilepsy with two competitions to detect and predict seizure onset.

The Seizure Detection and Prediction Challenge, an international competition sponsored by the American Epilepsy Society (AES), National Institutes of Health’s National Institute of Neurological Disorders and Stroke (NINDS) and the Epilepsy Foundation, challenges experts to detect and predict seizure activity accurately. In the first phase, seizure detection, contestants are charged with analyzing retrospective prolonged intracranial EEG data recorded from four dogs with naturally occurring epilepsy and from eight patients with medication-resistant seizures during evaluation for epilepsy surgery. The contestant or group that can identify the earliest EEG changes leading to seizures with the fewest false alarms wins $8,000.

A second phase, the seizure prediction challenge, will follow and award the winning contestant or group $20,000 for using the same data set to predict seizures in advance of their clinical onset with the highest accuracy.

Neurostimulation represents a possible therapy capable of aborting seizures before they affect a patient's normal activities. However, in order for a responsive neurostimulation device to successfully stop seizures, a seizure must be detected and electrical stimulation applied as early as possible.

“Accurate seizure detection and prediction are key to building effective devices to treat epilepsy,” says Brian Litt, MD, co-chair of the AES Presidential Symposium, professor of Neurology and Bioengineering at the University of Pennsylvania and director of Penn’s new Center for Neuroengineering and Therapeutics. Litt, with symposium co-chair Gregory Worrell, MD, PhD, Professor of Neurology, Biomedical Engineering and Physiology at the Mayo Clinic, are coordinating the competitions, and will announce the winners of both competitions at the AES Presidential Symposium in Seattle on Saturday, December 8th. Elson So, MD, also of the Mayo Clinic, is the current president of the American Epilepsy Society and the host of the symposium.

Click here to view the full release.

Multimedia