Preictal-Interictal Classification for Seizure Prediction
Bibliographic record
Abstract
Epilepsy is one of the most prevalent neurological disorders, affecting more than 50 million people worldwide. Seizures are a common symptom of epilepsy, which manifest abruptly and cause disruption in a patient’s life. Epileptic seizures can lead to serious injury, and people with untreatable epilepsy must live with the uncertainty of the next seizure occurrence. The ability to predict the occurrence of a seizure could alleviate many of the risks people with epilepsy face. Patients would have time to take precautions to reduce the risk of injury or prevent the seizure altogether. Most of the current approaches are focused on detecting seizures when they occur. While these approaches are useful, they do not provide any lead time to take preventive measures. It is widely known that the brain activity before an actual seizure is a strong indicator of an upcoming seizure. Therefore, we approach this problem from a prediction lens, by developing a classifier that can separate the pre-seizure state from regular brain activity. Development of such a classifier with high performance will provide a lead time to take preventive measures to handle an incoming seizure. The classification model used customized convolutional neural networks trained on short-time Fourier transform images to learn features from multi-channel intracranial electroencephalography (iEEG). The model was trained on a large publicly available dataset (SWEC-ETHZ iEEG database) containing over 2500 hours of EEG data from 18 patients. We have performed these experiments on the data of 9 patients in the database with varying results, highest being an AUC of 0.86.
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 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".