Crowdsourced algorithms help predict epileptic seizures

Epileptic seizure prediction is now possible in a wider range of patients than previously thought, thanks to the crowdsourcing of more than 10,000 algorithms worldwide.

In 2016, Australian and US researchers ran the Melbourne University AES/MathWorks/NIH Seizure Prediction Challenge on the online data science competition platform Kaggle, focused on seizure prediction using long-term electrical brain activity recordings from humans obtained in 2013 from the implantable NeuroVista Seizure Advisory System. The challenge? To distinguish between 10-minute clips of two distinct states: brain activity in the hour immediately prior to a seizure and ‘interictal activity’, or the times between seizures.

“Epilepsy affects 65 million people worldwide,” said Dr Levin Kuhlmann, from the University of Melbourne’s Graeme Clark Institute and St Vincent’s Hospital Melbourne. “We wanted to draw on the intelligence from the best international data scientists to achieve advances in epileptic seizure prediction performance for patients whose seizures were the hardest to predict.”

The contest attracted contestants from around the world, with 478 teams and over 646 participants developing more than 10,000 algorithms to distinguish between the 10-minute inter-seizure verses pre-seizure data clips. The top algorithms were tested on the patients with the lowest seizure prediction performance based on previous studies, with the results published in Brain: A Journal of Neurology.

“Our evaluation revealed on average a 90% improvement in seizure prediction performance, compared to previous results,” Dr Kuhlmann said. “Epilepsy is highly different among individuals. Results showed different algorithms performed best for different patients, supporting the use of patient-specific algorithms and long-term monitoring.”

Building on this success, researchers have developed Epilepsyecosystem.org, an online ecosystem for algorithm and data sharing to further develop and improve seizure prediction. The top algorithms in the ecosystem will be invited for evaluation on the full clinical trial database, with the aim of finding the best algorithms for the widest range of patients.

“Accurate seizure prediction will transform epilepsy management by offering early warnings to patients or triggering interventions,” Dr Kuhlmann said. “Our results highlight the benefit of crowdsourcing an army of algorithms that can be trained for each patient and the best algorithm chosen for prospective, real-time seizure prediction.

“The hope is to make seizures less like earthquakes, which can strike without warning, and more like hurricanes, where you have enough advance warning to seek safety.”

Image credit: ©stock.adobe.com/au/Kateryna_Kon