A Novel Seizure Prediction Method Based on Probability Density Distribution of Poincare Chaos

Epilepsy affects 50 million population in the world and the death rate of sudden unexpected death in epilepsy (SUDEP) is the top of death rate of this population. Unfortunately, seizure prediction with a time horizon of minutes to hours remains an open issue and a clinically applicable solution is still not available. In our research, a novel seizure prediction method based on probability density distribution of Poincare chaos is introduced. The prediction time started to count when out risk probability is over 70% occurrence to seizure onset. Finally, our average prediction time is 24.96 +/- 18.09 minutes, excluding ten cases for miss prediction and six events for risk probability less than 70%.