Una Europa Epilepsy Data Challenge
BIOMED - KU Leuven - Belgium
AI-based Seizure Detection With Wearable EEG
The Seizure Detection Challenge, in collaboration with Una Europa, aims at developing innovative and robust machine learning (ML) frameworks for electroencephalography (EEG) data processing, in which the end use case is detection of epileptic seizures.
In patients with epilepsy, lifelong treatment with antiseizure medications may be required, as relapse after withdrawal is high and even patients who are considered to be seizure free under treatment, can still relapse. It is, therefore, paramount to accurately detect seizures to improve therapeutic decisions. However, the subtle clinical manifestation of seizures hampers the patient’s and the caregiver’s ability to correctly report the seizure in the seizure diary, as serious underreporting of seizures in self diaries has been reported. As such, the seizure diary is an unreliable method, although commonly used in clinical practice as well as surrogate endpoint in trials for antiseizure medication. Automated EEG-based seizure detection systems are a useful support tool to objectively detect and register seizures during long-term video-EEG recording. However, this standard full scalp-EEG recording setup is of limited use outside the hospital, and a discreet, wearable device is needed for capturing seizures in the home setting. A wearable device that records EEG with behind-the-ear (bhe) electrodes, the SensorDot (SD) of Byteflies, has been developed during SeizeIT study. This CE-marked device is a user-friendly wearable that makes use of two behind-the-ear channels to detect seizures.
Within the scope of this challenge, participants will be presented with a task focused on training ML models to accurately detect seizure events in data obtained from the SD wearable device.
More information about the dataset and regulations can be found in this website.
Important Dates
- Challenge duration: February - May 2025
- Registration deadline: 20 January 2025
- Joint kick-off session: 3 February 2025
- Joint workshop: 23-24 April 2025
- End of challenge: 16 May 2025