International Epilepsy Electrophysiology Portal

A team of researchers from Penn and the Mayo Clinic has challenged the best minds in science and “machine learning” to improve devices to predict epileptic seizure activity and to do so accurately. This competition is hosted on Kaggle.com and the ieeg.org. Up to $25,000 in prizes will be rewarded to the teams that provide the best results by the end of the competition.

The Competition
Intracranial EEG was recorded from dogs with naturally occurring epilepsy using an ambulatory monitoring system. EEG was sampled from 16 electrodes at 400 Hz, and recorded voltages were referenced to the group average. These are long duration recordings, spanning multiple months up to a year and recording up to a hundred seizures in some dogs.

Ambulatory EEG recording system
In addition, datasets from patients with epilepsy undergoing intracranial EEG monitoring to identify a region of brain that can be resected to prevent future seizures are included in the contest. These datasets have varying numbers of electrodes and are sampled at 5000 Hz, with recorded voltages referenced to an electrode outside the brain. The challenge is to distinguish between ten minute long data clips covering an hour prior to a seizure, and ten minute iEEG clips of interictal activity. Seizures are known to cluster, or occur in groups. Patients who typically have seizure clusters receive little benefit from forecasting follow-on seizures. For this contest only lead seizures, defined here as seizures occurring four hours or more after another seizure, are included in the training and testing data sets. In order to avoid any potential contamination between interictal, preictal, and post-ictal EEG signals interictal segments in the canine training and test data were restricted to be at least one week before or after any seizure. In the human data, where the entire monitoring session may last less than one week, interictal data segments were restricted to be at least four hours before or after any seizure. Interictal data segments were chosen at random within these restrictions for both canine and human subjects.

Participants are invited to visit the NIH-sponsored International Epilepsy Electrophysiology portal (http://ieeg.org) to review and download annotated interictal and preictal data from other patients and animal subjects. Using ieeg.org data for additional algorithm training is permitted.

Acknowledgements:
This competition is sponsored by the National Institutes of Health (NINDS), the Epilepsy Foundation, and the American Epilepsy Society.