Seizure Prediction Using Bidirectional LSTM

TL;DR

This paper explores the use of bidirectional LSTM neural networks to predict epileptic seizures from EEG data, achieving improved accuracy over previous models and potentially enabling better patient care.

Contribution

The study demonstrates that bidirectional LSTM models outperform traditional SVM and GRU networks in seizure prediction tasks using EEG data.

Findings

Achieved an AUC of 0.84 on test data.

Bidirectional LSTM outperforms SVM and GRU models.

Model shows promise for real-time seizure prediction.

Abstract

Approximately, 50 million people in the world are affected by epilepsy. For patients, the anti-epileptic drugs are not always useful and these drugs may have undesired side effects on a patient's health. If the seizure is predicted the patients will have enough time to take preventive measures. The purpose of this work is to investigate the application of bidirectional LSTM for seizure prediction. In this paper, we trained EEG data from canines on a double Bidirectional LSTM layer followed by a fully connected layer. The data was provided in the form of a Kaggle competition by American Epilepsy Society. The main task was to classify the interictal and preictal EEG clips. Using this model, we obtained an AUC of 0.84 on the test dataset. Which shows that our classifier's performance is above chance level on unseen data. The comparison with the previous work shows that the use of bidirectional LSTM networks can achieve significantly better results than SVM and GRU networks.