Using Long Short-Term Memory (LSTM) recurrent neural networks to classify unprocessed EEG for seizure prediction
Removing the need to perform feature engineering is an advancement on previously published models. This framework can be applied to many different patients' needs and a variety of acute interventions. Also, it opens the possibility of personalized seizure predictions that can be altered to meet daily needs.
Authors
- Anthony N. Burkitt (ORCID: https://orcid.org/0000-0001-5672-2772)
- David B. Grayden (ORCID: https://orcid.org/0000-0002-5497-7234)
- Mark Cook (ORCID: https://orcid.org/0000-0002-8875-4135)
- Jordan D. Chambers (ORCID: https://orcid.org/0000-0002-6760-2079)
Institutions
- The University of Melbourne (AU)
- St Vincent's Hospital Melbourne (AU)
Publication Details
- Journal
- Frontiers in Neuroscience
- Published
- 2024-11-15
- DOI
- https://doi.org/10.3389/fnins.2024.1472747
- Citations
- 12
- Primary Topic
- EEG and Brain-Computer Interfaces
- Type
- article
- Field-Weighted Citation Impact
- 4.11
Funders
- University of Melbourne