SYDNEY, Aug. 9 (Xinhua) -- An Australian-led study has adopted 10,000 crowdsourced algorithms to better predict epileptic seizures.
"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," Dr. Levin Kuhlmann from the University of Melbourne's Graeme Clarke Institute and St. Vincent's Hospital said.
"Accurate seizure prediction will transform epilepsy management by offering early warnings to patients or triggering interventions."
Published on Thursday, the research began with a world-wide mathematical data science challenge in 2016.
Contestants were tasked with designing algorithms that could effectively distinguish between a pre-seizure and an inter-seizure.
With more than 646 participants and 478 teams, the most accurate algorithms were tested on patients with the lowest seizure prediction rates.
"Our evaluation revealed on average a 90-percent improvement in seizure prediction performance, compared to previous results," Kuhlmann said.
Effecting over 65 million people around the world, epilepsy can be "highly different" among individual sufferers.
"Results showed different algorithms performed best for different patients, supporting the use of patient-specific algorithms and long-term monitoring," Kuhlmann said.
Encouraged by the positive findings, researchers have now developed an algorithm and data sharing website called Epilepsy Ecosystem, to encourage others to share their work and help build on the project.
"It's about bringing together the world's best data scientists and pooling the greatest algorithms to advance epilepsy research," 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."
