Epilepsy seizure prediction with few-shot learning method

Abstract

Epileptic seizures prediction and timely alarms allow the patient to take effective and preventive actions. In this paper, a convolutional neural network (CNN) is proposed to diagnose the preictal period. Our goal is for those epileptic patients in whom seizures occur late and it is very challenging to record the preictal signal for them. In the previous works, generalized methods were inevitably used for this group of patients which were not very accurate. Our approach to solve this problem is to provide a few-shot learning method. This method, having the previous knowledge, is trained with only a small number of samples, learns new tasks and reduces the efforts to collect more data. Evaluation results for three patients from the CHB–MIT database, for a 10-min seizure prediction horizon (SPH) and a 20-min seizure occurrence period (SOP), averaged sensitivity of 95.70% and a false prediction rate (FPR) of 0.057/h and for the 5-min prediction horizon and the 25-min seizure occurrence period averaged sensitivity of 98.52% and a false prediction rate of (FPR) of 0.045/h. The proposed few-shot learning method, based on previous knowledge gained from the generalizable method, is regulated with a few new patient samples for the patient. Our results show that the accuracy obtained in this method is higher than the generalizable methods.

Addressing data limitations in seizure prediction through transfer learning

“…Several algorithms have been proposed to evaluate the effectiveness of transfer learning in seizure prediction 11 , 16 , 28 , 29 , 43 . These studies reported improved performance and computational efficiency, consistent with the findings of this experiment.…”

“…Despite the DCAE being trained on data from a different database with distinct acquisition systems, it was evident that the models benefited from using pretrained weights. Several algorithms have been proposed to evaluate the effectiveness of transfer learning in seizure prediction 11,16,28,29,43 . These studies reported improved performance and computational efficiency, consistent with the findings of this experiment.…”

“…For the transfer learning, they performed leave-one-patient-out by training the model with N-1 patients and fine-tuning it with the remaining one. Nazari et al 28 proposed a few-shot learning model. They trained a DCNN using data from 15 patients, froze the convolutional layers, and fine-tuned the classification layers for each patient individually.…”