Uncovering the structure of clinical EEG signals with self-supervised\n learning
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Objective. Supervised learning paradigms are often limited by the amount of\nlabeled data that is available. This phenomenon is particularly problematic in\nclinically-relevant data, such as electroencephalography (EEG), where labeling\ncan be costly in terms of specialized expertise and human processing time.\nConsequently, deep learning architectures designed to learn on EEG data have\nyielded relatively shallow models and performances at best similar to those of\ntraditional feature-based approaches. However, in most situations, unlabeled\ndata is available in abundance. By extracting information from this unlabeled\ndata, it might be possible to reach competitive performance with deep neural\nnetworks despite limited access to labels. Approach. We investigated\nself-supervised learning (SSL), a promising technique for discovering structure\nin unlabeled data, to learn representations of EEG signals. Specifically, we\nexplored two tasks based on temporal context prediction as well as contrastive\npredictive coding on two clinically-relevant problems: EEG-based sleep staging\nand pathology detection. We conducted experiments on two large public datasets\nwith thousands of recordings and performed baseline comparisons with purely\nsupervised and hand-engineered approaches. Main results. Linear classifiers\ntrained on SSL-learned features consistently outperformed purely supervised\ndeep neural networks in low-labeled data regimes while reaching competitive\nperformance when all labels were available. Additionally, the embeddings\nlearned with each method revealed clear latent structures related to\nphysiological and clinical phenomena, such as age effects. Significance. We\ndemonstrate the benefit of self-supervised learning approaches on EEG data. Our\nresults suggest that SSL may pave the way to a wider use of deep learning\nmodels on EEG data.\n
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it