Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.08959 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917135755771904 |
|---|---|
| author | Kastrati, Ard Bürki, Josua Lauer, Jonas Xuan, Cheng Iaquinto, Raffaele Wattenhofer, Roger |
| author_facet | Kastrati, Ard Bürki, Josua Lauer, Jonas Xuan, Cheng Iaquinto, Raffaele Wattenhofer, Roger |
| contents | We introduce a unified benchmarking framework focused on evaluating EEG-based foundation models in clinical applications. The benchmark spans 11 well-defined diagnostic tasks across 14 publicly available EEG datasets, including epilepsy, schizophrenia, Parkinson's disease, OCD, and mild traumatic brain injury. It features minimal preprocessing, standardized evaluation protocols, and enables side-by-side comparisons of classical baselines and modern foundation models. Our results show that while foundation models achieve strong performance in certain settings, simpler models often remain competitive, particularly under clinical distribution shifts. To facilitate reproducibility and adoption, we release all prepared data and code in an accessible and extensible format. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_08959 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications Kastrati, Ard Bürki, Josua Lauer, Jonas Xuan, Cheng Iaquinto, Raffaele Wattenhofer, Roger Machine Learning Artificial Intelligence We introduce a unified benchmarking framework focused on evaluating EEG-based foundation models in clinical applications. The benchmark spans 11 well-defined diagnostic tasks across 14 publicly available EEG datasets, including epilepsy, schizophrenia, Parkinson's disease, OCD, and mild traumatic brain injury. It features minimal preprocessing, standardized evaluation protocols, and enables side-by-side comparisons of classical baselines and modern foundation models. Our results show that while foundation models achieve strong performance in certain settings, simpler models often remain competitive, particularly under clinical distribution shifts. To facilitate reproducibility and adoption, we release all prepared data and code in an accessible and extensible format. |
| title | EEG-Bench: A Benchmark for EEG Foundation Models in Clinical Applications |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2512.08959 |