Predicting epileptic seizures in advance
- Submitting institution
-
Heriot-Watt University
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 10596364
- Type
- D - Journal article
- DOI
-
10.1371/journal.pone.0099334
- Title of journal
- PLoS ONE
- Article number
- e99334
- First page
- -
- Volume
- 9
- Issue
- 6
- ISSN
- 1932-6203
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2014
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
1
- Research group(s)
-
-
- Citation count
- 49
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Funded by a SICSA studentship in a competition to encourage interdisciplinary advances. Early discussions with clinicians at the Edinburgh Royal Infirmary steered us towards approaches that could exploit individual patient data without overfitting, since EEGs are highly individual. This led to our novel (in the area) use of feature extraction as part of the process. Subsequently, our method achieved leading performance across a recognised dataset of 21-patients (a relatively large number in this field), and became an exemplar of proof of concept that has been cited by a number of subsequent influential reviews in both the neurology and computing.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
