Penn, Mayo Clinic Launch ‘Seizure Detection Challenge’

The challenge, designed by Penn and the Mayo Clinic, is an attempt to help researchers combat medication-resistant epilepsy.

The University of Pennsylvania, Mayo Clinic and other groups announced a program called Seizure Detection Challenge with $8,000 in prizes. The challenge is hosted by Kaggle.com, a site where researchers can crowdsource data. And here I thought crowdsourcing was just good to figure out what movie you want to see. The challenge is an attempt to help researchers combat medication-resistant epilepsy.

Here’s how it works:

Contestants will analyze 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.

EEG is a recording of spontaneous brain activity and is generally used to diagnose epilepsy.


If you're confused, the Kaggle site includes this amazing diagram of the "Dog Recording System."

DogRecordingSystem

“Leveraging the tremendous talent of scientists and the machine learning community worldwide has a great potential to help researchers and our patients. It’s an exciting new model for collaboration”, added co-primary investigator Brian Litt, MD, professor of Neurology and Bioengineering at the University of Pennsylvania and director of the new Penn Center for Neuroengineering and Therapeutics.

The program runs through August 19th. It's funded by the American Epilepsy Society and the National Institute of Neurological Disorders and Stroke.

Be respectful of our online community and contribute to an engaging conversation. We reserve the right to ban impersonators and remove comments that contain personal attacks, threats, or profanity, or are flat-out offensive. By posting here, you are permitting Philadelphia magazine and Metro Corp. to edit and republish your comment in all media.