Neural Complexity and Prognosis: Predicting Recovery in Pediatric Epilepsy Using EEG Markers
Bibliographic record
Abstract
Predicting patient functional outcomes is an indispensable part of clinical care in the Pediatric Intensive Care Unit (PICU), especially for children with epilepsy, a prominent neurological emergency. Electroencephalography (EEG) is a dynamic tool for assessing brain activity, with brain complexity and spectral power features emerging as predictors of consciousness recovery. We investigated whether patients’ EEG activity under anesthesia could predict their recovery, using data from 12 pediatric epilepsy patients (mean age: 11.0±2.2 years). Neural complexity, the intricacy of connectivity between brain regions, is heavily implicated in a patient’s capacity for consciousness. We hypothesize that neural complexity will be a stronger predictor of patient outcomes than spectral power and that higher complexity will be associated with better outcomes. EEG features were analyzed during sedated, baseline (non-sedated), and difference states. Recovery was assessed three months post-injury using the Glasgow Outcome Scale-Extended (GOS-E). The predictive performance of significant EEG markers was evaluated using logistic regression with leave-one-out cross-validation and permutation testing. Baseline EEG features showed minimal prognostic power, whereas sedation and difference states yielded high prognostic accuracy. In the sedated state, the complexity features rate entropy and Lopez-Ruiz-Mancini-Calbet Complexity (HC-LMC) predicted recovery, separating good and poor outcomes with 100% accuracy. These findings demonstrate that EEG markers of complexity can predict the recovery of consciousness in pediatric epilepsy patients under anesthesia. Therefore, EEG analysis could be an accessible, accurate, and powerful prognostic tool in clinical settings. Future research should explore these results in larger samples to validate the findings that rate entropy and HC-LMC are predictive of recovery. Further, these features should be studied in patients of different etiologies to analyze their potential as generalizable markers of consciousness.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".