2.23 Acute concussion classification with a deep neural network using only 3 EEG sensors
Bibliographic record
Abstract
Objective To develop a clinically feasible, brain-based tool for sideline concussion classification. Design Prospective cohort study. Setting High school athletes. Participants 35 healthy control male athletes; 23 male athletes with concussion. Interventions (or Assessment of Risk Factors) N/A Outcome Measures (1) Clinical assessment of concussion by a physician with expertise in concussion using diagnostic criteria consistent with the Berlin consensus statement. (2) Assessment of symptoms using SCAT-3 or Child SCAT-3. (3) 5 minutes of raw, resting state EEG data. Main Results All of the concussed participants met the Berlin criteria and exhibited between 4 to 22 SCAT3 symptoms, at the time of testing. Using our previously trained deep learning network on 64 EEG channels, we identified the top three channels that had the highest impact on concussion classification and re-trained the network using these three channels. We found that the re-trained network classified concussion with an accuracy of 93.3% (SD=.005, 95% CI=.926, .940). All three channels were located in the occipital region of the head. Conclusions This is the first proof of concept showing that a deep learning network can be trained for concussion classification using raw, resting state data from only 3 EEG sensors. This is a critical step in developing a portable, easy to use EEG systems that can be used in a clinical setting and for sideline assessment of concussion.
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.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".