Deep learning models using intracranial and scalp EEG for predicting sedation level during emergence from anaesthesia
The combination of iEEG and scalp EEG better predicted sedation level than either modality alone. The scalp EEG only model achieved a similar AUC to the combined model and maintained its performance in additional patients, suggesting that scalp EEG models are likely sufficient for real-time monitoring. Deep learning approaches using multiple leads to capture a wider area of brain activity may help augment existing EEG monitors for prediction of sedation.
Authors
- Babak Razavi
- Lichy Han (ORCID: https://orcid.org/0000-0002-5785-0968)
- Kimford J. Meador (ORCID: https://orcid.org/0000-0002-7471-882X)
- David Arnold Purger (ORCID: https://orcid.org/0000-0003-4668-1174)
- Vivek Buch (ORCID: https://orcid.org/0000-0003-1151-6128)
- Sarah L. Eagleman (ORCID: https://orcid.org/0000-0003-1584-7135)
- David R. Drover (ORCID: https://orcid.org/0000-0001-6633-3295)
- Casey H. Halpern (ORCID: https://orcid.org/0000-0003-3907-216X)
- Samantha Gaston
Institutions
- Stanford Medicine (US)
- University of Pennsylvania (US)
- Stanford University (US)
Publication Details
- Journal
- BJA Open
- Published
- 2024-10-12
- DOI
- https://doi.org/10.1016/j.bjao.2024.100347
- Citations
- 3
- Primary Topic
- Anesthesia and Sedative Agents
- Type
- article
- Field-Weighted Citation Impact
- 1.92
Funders
- National Institutes of Health