Dr Andriy Temko, a research fellow at the INFANT centre, was named winner of the Kaggle challenge.
Dr Andriy Temko, a research fellow at the INFANT centre, was named winner of the Kaggle challenge.

A UCC researcher has won a prestigious international competition for his work in predicting seizures in the human brain through long-term EEG recordings.

Dr Andriy Temko, a research fellow at the INFANT centre, was named as winner of the Kaggle challenge, and a $10,000 first prize.

Together with data scientists from Ornon, France; Curitiba, Brazil; and Minneapolis, US, Dr Temko developed an artificial intelligence solution that showed the highest accuracy among nearly 500 competing teams from around the world.

The aim of the event was to develop seizure forecasting systems with the potential to help patients with epilepsy lead more normal lives. Epilepsy afflicts nearly 1% of the world’s population, and is characterised by the occurrence of spontaneous seizures.

The challenge was organised and sponsored by the National Institute of Health, American Epilepsy Society and Melbourne University.

In order for electrical brain activity (EEG) based seizure forecasting systems to work effectively, computational algorithms must reliably identify periods of increased probability of seizure occurence. If these brain states can be identified, devices designed to warn patients of impending seizures would be possible. Patients could avoid potentially dangerous activities like driving or swimming, and medications could be administered only when needed to prevent seizures, reducing overall side effects.

For more information, visit: https://www.kaggle.com/c/melbourne-university-seizure-prediction

Dr Temko is a PI of the Wellcome Trust Seed Award in Science. In collaboration with Dr. Emanuel Popovici and Prof. Geraldine Boylan, he is working on the development of a newborn smart brain ‘stethoscope‘ — a portable device that will allow a medical professional to listen to an infant’s brainwaves and quickly assess their brain health status. Such a low cost device for sound-based observation of brain health could be used by all healthcare professionals globally, greatly improving access to diagnosis and treatment for disadvantaged communities.