An algorithm for seizure detection in rodents
Bibliographic record
Abstract
OBJECTIVE: Epilepsy animal research often relies on long-term intracranial electroencephalographic (iEEG) recordings. Here, we describe an artificial neural network (ANN) algorithm for automatic detection of seizures. METHODS: The algorithm was trained on iEEG recordings of three mouse models of chronic epilepsy: (1) the pilocarpine model of epilepsy induced by status epilepticus; (2) the albumin model of seizures induced by blood-brain barrier opening; and (3) the synapsin triple knockout (STKO) model of genetic epilepsy. The iEEG signals were filtered, segmented, and underwent feature extraction to be classified by ANN. For classifier training, a dataset of seizure and non-seizure recordings was comprised and represented by 22 extracted features. Forward selection analysis was applied for the identification of an optimal feature subset. A graphical user interface was created for the simple execution of data analysis and seizure detection. System performance was assessed by analyzing over 2800 h of iEEG recordings from 15 animals. The developed system achieved a sensitivity and positive predictive value of above 98%. RESULTS: Since the development of this system in 2010, it has been used to study seizure frequency in multiple mouse and rat models of status epilepticus and post-traumatic epilepsy (compared to sham controls), as well as in young and old controls. SIGNIFICANCE: We conclude that the proposed approach is a reliable and efficient method for the automatic detection of seizures in mice and rats. PLAIN LANGUAGE SUMMARY: Epilepsy research often relies on rodent experiments involving EEG (electroencephalography) recordings. Today, most researchers still rely on manual inspection of these recordings in order to find and count seizures. This paper describes AI software for automated seizure detection in mice and rats. Over the past 15 years, this algorithm has been used in multiple studies of conditions that cause seizures.
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 | 0.001 | 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) | 0.008 | 0.003 |
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".