NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces

• URL: http://arxiv.org/abs/2605.14698v1
• Date: Thu, 14 May 2026 11:13:41 GMT
• Title: NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces
• Abstract summary: Foundation models promise to extract unified representations that generalize across downstream tasks.<n>EEG-specific FMs do not consistently outperform time-series FMs.<n>Current models do not yet deliver on the promise of an out-of-the-box unified EEG model.
• Score: 24.672695443264995
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular field. Published evaluations differ in datasets, in the EEG-specific preprocessing that might influence reported results, and in the reported metrics, frequently obscuring the clinical relevance in EEG. We introduce NeuroAtlas, the largest EEG benchmark to date: 42 datasets and 260k hours covering clinical EEG (epilepsy, sleep medicine, brain age estimation) and brain-computer interfaces, and include multiple datasets per task along with bespoke clinical evaluation metrics. Besides evaluating EEG-FMs with respect to supervised baselines, we present results from generic time-series FMs. We report three findings. First, EEG-specific FMs do not consistently outperform time-series FMs, which have neither EEG-focused architectures nor been pretrained on EEG. Second, standard machine learning metrics are insufficient to assess clinical utility: thus, we thoroughly evaluate more appropriate measures such as the quality of event-level decision-making, hypnogram-derived features, and the brain-age gap in the domains of epilepsy, sleep, and brain age, respectively. Third, model rankings and performance can vary substantially within domains. We conclude that pretrained models perform largely on par, with only narrow advantages for a few, and that current models do not yet deliver on the promise of an out-of-the-box unified EEG model. NeuroAtlas exposes this gap and provides the datasets and metrics for the next generation of unified EEG FMs.

Related papers

• OmniEEG-Bench: A Standardized Evaluation Benchmark for EEG Foundation Models [22.964421663748755]
  We introduce OmniEEG-Bench, a unified benchmark and downstream task roadmap for EEG foundation models (FMs)<n>It organizes evaluation of EEG FMs into six task families spanning (i) signal reliability, (ii) biometrics and disease, (iii) consciousness and state, (iv) cognition and emotion, (v) naturalistic stimulus decoding, and (vi) motor and interaction.<n>We benchmark 10 representative EEG foundation models and report a leaderboard that covers diverse evaluation settings.
  arXiv  Detail & Related papers  (2026-05-30T17:20:04Z)
• A Multi-dimensional Framework for Evaluating Generalization in EEG Foundation Models [48.385356148620815]
  Recent EEG foundation models have demonstrated promising transfer capabilities across tasks and datasets.<n>We propose a multi-dimensional evaluation framework for assessing EEG models under realistic low-resource conditions.
  arXiv  Detail & Related papers  (2026-05-27T14:51:54Z)
• CLEF: EEG Foundation Model for Learning Clinical Semantics [50.3767252824646]
  We introduce CLEF, a clinically grounded long-context EEG foundation model.<n>We evaluate CLEF on a new 234-task benchmark spanning disease phenotypes, medication exposures, and EEG findings.
  arXiv  Detail & Related papers  (2026-05-11T16:34:58Z)
• Omni-iEEG: A Large-Scale, Comprehensive iEEG Dataset and Benchmark for Epilepsy Research [4.4167069169736655]
  $textbf Omni-iEEG is a large-scale, pre-surgical iEEG resource comprising $textbf302 patients$ and $textbf178 hours$ of high-resolution recordings.<n>It includes harmonized clinical metadata such as seizure onset zones, resections, and surgical outcomes, validated by board-certified epileptologists.<n>It defines clinically meaningful tasks with unified evaluation metrics grounded in clinical priors, enabling systematic evaluation of models in clinically relevant settings.
  arXiv  Detail & Related papers  (2026-02-17T22:55:11Z)
• EEGDM: EEG Representation Learning via Generative Diffusion Model [17.595769291603688]
  We propose an EEG representation learning framework building upon Generative Diffusion Model (EEGDM)<n>Specifically, we developed a structured state-space model for diffusion pretraining and trained it using Denoising Diffusion Probabilistic Model (DDPM) framework.<n>The resulting latent EEG representations were then used for downstream classification tasks via our proposed latent fusion transformer (LFT)
  arXiv  Detail & Related papers  (2025-08-13T14:40:52Z)
• NeuroDx-LM: A Clinical Large-Scale Model for EEG-based Neurological Disorder Detection [7.185477956123345]
  Large-scale models pre-trained on Electroencephalography (EEG) have shown promise in clinical applications such as neurological disorder detection.<n>NeuroDx-LM is a novel large-scale model specifically designed for detecting EEG-based neurological disorders.
  arXiv  Detail & Related papers  (2025-08-11T16:02:25Z)
• EEG Foundation Models: A Critical Review of Current Progress and Future Directions [4.096453902709292]
  Self-supervised EEG encoders have sparked a transition towards general-purpose EEG foundation models (EEG-FMs)<n>This study reviews 10 early EEG-FMs and presents a critical synthesis of their methodology, empirical findings, and outstanding research gaps.
  arXiv  Detail & Related papers  (2025-07-15T22:52:44Z)
• BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals [46.121056431476156]
  This paper proposes Brain Omni, the first brain foundation model that generalises across heterogeneous EEG and MEG recordings.<n>Existing approaches typically rely on separate, modality- and dataset-specific models, which limits performance and cross-domain scalability.<n>A total of 1,997 hours of EEG and 656 hours of MEG data are curated and standardised from publicly available sources for pretraining.
  arXiv  Detail & Related papers  (2025-05-18T14:07:14Z)
• RISE-iEEG: Robust to Inter-Subject Electrodes Implantation Variability iEEG Classifier [0.0]
  Intracranial electroencephalography (iEEG) is increasingly used for clinical and brain-computer interface applications.<n>We introduce a novel decoder model that is robust to inter-subject electrode implantation variability.<n>We call this model RISE-iEEG, which stands for Robust to Inter-Subject Electrode Implantation Variability iEEG.
  arXiv  Detail & Related papers  (2024-08-12T18:33:19Z)
• Task-oriented Self-supervised Learning for Anomaly Detection in Electroencephalography [51.45515911920534]
  A task-oriented self-supervised learning approach is proposed to train a more effective anomaly detector. A specific two branch convolutional neural network with larger kernels is designed as the feature extractor. The effectively designed and trained feature extractor has shown to be able to extract better feature representations from EEGs.
  arXiv  Detail & Related papers  (2022-07-04T13:15:08Z)
• Data augmentation for learning predictive models on EEG: a systematic comparison [79.84079335042456]
  deep learning for electroencephalography (EEG) classification tasks has been rapidly growing in the last years. Deep learning for EEG classification tasks has been limited by the relatively small size of EEG datasets. Data augmentation has been a key ingredient to obtain state-of-the-art performances across applications such as computer vision or speech.
  arXiv  Detail & Related papers  (2022-06-29T09:18:15Z)
• A Novel Transferability Attention Neural Network Model for EEG Emotion Recognition [51.203579838210885]
  We propose a transferable attention neural network (TANN) for EEG emotion recognition. TANN learns the emotional discriminative information by highlighting the transferable EEG brain regions data and samples adaptively. This can be implemented by measuring the outputs of multiple brain-region-level discriminators and one single sample-level discriminator.
  arXiv  Detail & Related papers  (2020-09-21T02:42:30Z)
• Uncovering the structure of clinical EEG signals with self-supervised learning [64.4754948595556]
  Supervised learning paradigms are often limited by the amount of labeled data that is available. This phenomenon is particularly problematic in clinically-relevant data, such as electroencephalography (EEG) By extracting information from unlabeled data, it might be possible to reach competitive performance with deep neural networks.
  arXiv  Detail & Related papers  (2020-07-31T14:34:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.