Machine learning for physiological monitoring and epilepsy diagnosis

The scope of the project is monitoring physiological patients with epilepsy and using machine learning to improve the diagnosis speed and accuracy of clinicians. The project will start with monitoring short-term outpatient EEG of epilepsy patients, both at the Alfred and Epworth Eastern hospitals to facilitate automated labelling of EEG data for epilepsy patients. As more long-term wearables data are collected by the Epilepsy team at the Alfred and Epworth Eastern, the project will transition to cover analytics for long-term monitoring of epilepsy additionally. The research will be conducted in 2 main stages. The objective of the first stage is to evaluate existing techniques involved in detection of epileptiform activity. This stage will also involve developing new techniques based on the foundation of existing methods to produce more accurate results. With the addition of long-term data the second part of the project focuses on novel seizure detection/prediction methods.