Skip to main content

Epileptic Seizure Prediction

Primary supervisor

Levin Kuhlmann

Seizure prediction algorithms will be developed using the one-of-a-kind ultra-long-term human intracranial EEG dataset obtained from the Neurovista Corporation clinical trial of their Seizure Advisory System, or data from other implantable or wearable devices. This involves consideration of both feature-based machine learning or data science approaches and neural mass parameter estimation approaches to classify the EEG and predict seizures. Recent approaches focus on critical slowing as a marker for seizure susceptability and the influence of brain rhythms. We have also developed as a way to bring researchers, code and data together from all over the world to help solve the problem of seizure prediction. 

Required knowledge

Machine learning, AI, signal processing, dynamical systems theory are all relevant and can be learned. So too can the neuroscience.

Learn more about minimum entry requirements.