A P300-classification and spike-detection based study of the cognitive and memory impairment in epilepsy

For the patients with epilepsy affected by cognitive impairment, we analysed their P300 signals during cognitive tasks and spike components during slow wave sleep. According to the abnormal P300 characteristics of patients with epilepsy, a transfer-learning-based multi-domain feature combined classification method was proposed to identify the P300 signals in patients with epilepsy. A spike detection method combined multiple features was proposed to automatically detect the number of spikes in slow wave sleep EEG. A stronger correlation was shown between the P300 classification accuracy and the epilepsy period than the P300 amplitude and the epilepsy period. It was also found that the spike frequency during slow wave sleep of patients with epilepsy detected using this detector also had a significant negative correlation with the patients' P300 amplitude and P300 classification accuracy. A correlation between epileptic activity during sleep and cognitive performance in the waking state in epileptic patients was demonstrated, informing further studies using our proposed P300 classification method to assess the medical condition of patients with epilepsy and the treatment of epilepsy-related cognitive impairment.