| DOI | Resolve DOI: https://doi.org/10.1109/I2MTC60896.2024.10560863 |
|---|
| Author | Search for: Cook, Zara; Search for: Sinha, Grant; Search for: Wang, Jack; Search for: Zhao, Chengzong; Search for: Belacel, Nabil1; Search for: Doesburg, Sam; Search for: Medvedev, George; Search for: Ribary, Urs; Search for: Vakorin, Vasily; Search for: Xi, Pengcheng1ORCID identifier: https://orcid.org/0000-0003-3236-5234 |
|---|
| Affiliation | - National Research Council Canada. Digital Technologies
|
|---|
| Format | Text, Article |
|---|
| Conference | 2024 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), May 20-23, 2024, Glasgow, United Kingdom |
|---|
| Subject | EEG, diagnostics; generative machine learning; data augmentation; brain age prediction; accuracy; generative AI; transfer learning; predictive models; brain modeling; data models; electroencephalography |
|---|
| Abstract | Predicting the age of brain from EEG data holds significant promise for advancing healthcare diagnostics. By comparing predicted brain age with the biological age of patients, clinicians can gain valuable insights into the overall health status of individuals. To assist clinical decision making, the latest advance in AI research shows promise in the analysis of routine clinical data; however, challenges including limited availability of high-quality training data are limiting the full capacity of AI in neurology and clinical workflow. Therefore, this work proposes a novel approach using generative machine learning models to augment the training dataset for building models to predict brain age from EEG recordings. Our findings reveal that integrating synthetic data significantly boosts the performance of models. The study holds significant implications for neurological engineering, in particular for EEG-based age prediction tasks. |
|---|
| Publication date | 2024-05-20 |
|---|
| Publisher | IEEE |
|---|
| In | |
|---|
| Language | English |
|---|
| Peer reviewed | Yes |
|---|
| Export citation | Export as RIS |
|---|
| Report a correction | Report a correction (opens in a new tab) |
|---|
| Record identifier | 9cb34d6e-8db6-41d0-a7c4-a70e5326b9b4 |
|---|
| Record created | 2024-07-10 |
|---|
| Record modified | 2024-07-10 |
|---|
