Electroencephalography-Based Machine Learning Models for Predicting Ketogenic Diet Outcomes in Pediatric Drug-Resistant Epilepsy
Clinical Snapshot
PICO Framework
| P — Population | 90 pediatric patients with drug-resistant epilepsy |
| I — Intervention | EEG-based machine learning classifiers (19 different models) |
| C — Comparator | Different ML algorithms and EEG feature sets (absolute power, relative power, functional connectivity measures) |
| O — Outcomes | Prediction accuracy for ketogenic diet therapy response at 3 and 6 months (measured by recall, precision, F2 score, AUC) |
Bottom Line
This study evaluated EEG-based machine learning models to predict ketogenic diet therapy outcomes in 90 children with drug-resistant epilepsy. The best-performing models achieved moderate predictive accuracy (AUC ~0.60) with high recall but variable precision. While the concept of using EEG biomarkers to guide treatment selection is promising, several methodological limitations reduce confidence in these findings. The small sample size, single-center design, and lack of external validation limit generalizability. Critical diagnostic accuracy metrics like sensitivity, specificity, and confidence intervals were not reported. The modest AUC values suggest limited discriminative ability. Before clinical implementation, larger multi-center studies with external validation, proper blinding, and comprehensive diagnostic accuracy reporting are needed. The approach shows potential but requires substantial further development and validation.
Key Findings
P Value: Not reported for diagnostic accuracy metrics
Effect Size: Best 3-month model: recall=0.933, precision=0.767, F2=0.894; Best 6-month model: recall=0.759, precision=0.854, F2=0.776
Primary Outcome: Prediction accuracy for KDT response using EEG-based ML models
Nnt Or Sensitivity: Recall (sensitivity) ranges from 0.759 to 0.933 depending on model and timepoint
Confidence Interval: Not reported
Clinical Application
Requires specialized EEG analysis and ML infrastructure; may be challenging to implement in routine clinical practice Could complement existing epilepsy management pathways; would need validation in Australian pediatric epilepsy centers before clinical implementation Pediatric patients with drug-resistant epilepsy being considered for ketogenic diet therapy
Abstract
BACKGROUND: Ketogenic diet therapy (KDT) is an established treatment for drug-resistant epilepsy (DRE); however, methods for predicting its effectiveness remain underdeveloped. This study evaluated various machine learning (ML) models in predicting responses to KDT among DRE patients based on electroencephalography data. METHODS: Using leave-one-out cross-validation, this study evaluated 19 ML classifiers in predicting the outcomes of 90 DRE patients based on absolute and relative power, as well as functional connectivity measures (phase-locking value, phase lag index [PLI], and weighted PLI) across standard frequency bands. KDT significantly reduced seizure frequency at three and 6 months after initiation. RESULTS: The most effective classifier at 3 months was a Coarse Tree classifier trained on absolute power (recall = 0.933, precision = 0.767, F2 = 0.894, area under the receiver operating characteristic curve = 0.607). The most effective classifier at 6 months was a Gaussian Naive Bayes classifier trained on weighted PLI + relative power (recall = 0.759, precision = 0.854, F2 = 0.776, area under the receiver operating characteristic curve = 0.603). CONCLUSIONS: This study identified the most effective ML models for predicting KDT outcomes in DRE patients. The results highlight the potential of electroencephalography-based ML tools for guiding KDT treatment in clinical practice.
References
- 1.Hung, P. L., Chen, J. P., Lin, T. P., Hsieh, T. Y., Chen, Y. F., Su, T. Y., & Peng, S. J. (2026). Electroencephalography-Based Machine Learning Models for Predicting Ketogenic Diet Outcomes in Pediatric Drug-Resistant Epilepsy. Pediatric Neurology. https://doi.org/10.1016/j.pediatrneurol.2026.02.013
Related Research
Neurosurgical review
Bilateral decompressive craniectomy in pediatric patients: A systematic review.
1 June 2026
Neurosurgical review
Management of pediatric brain arteriovenous malformation: a systematic review of retrospective studies
29 May 2026
European journal of pediatrics
Machine learning-based integration of respiratory oscillometry and spirometry for predicting clinical outcomes in spinal muscular atrophy
13 May 2026
This content is for educational purposes for healthcare professionals only and does not constitute clinical advice. Clinical decisions should be based on individual patient assessment, current guidelines, and appropriate specialist consultation. Editorial Standards · Privacy Policy · Terms of Service