Related Experiment Video
Updated: Jun 7, 2025
Author Spotlight: A Unique Mouse Model of Asphyxia-Induced Cardiac Arrest
Published on: April 14, 2023
Prediction of Survival After Pediatric Cardiac Arrest Using Quantitative EEG and Machine Learning Techniques
Maayke Hunfeld1, Marit Verboom1, Sabine Josemans1
1From the Department of Neurology (M.H., M.V., S.J., A.v.R., D.S., R.v.d.B.), Erasmus MC, University Medical Center; Department of Neonatal and Pediatric Intensive Care, Division of Pediatric Intensive Care (M.H., C.B.), Erasmus MC Children's Hospital, Rotterdam; and Delft Institute of Applied Mathematics (F.L., G.J.), Delft University of Technology, the Netherlands.
Insights
Quantitative EEG (qEEG) and visual analysis of EEG background patterns 24 hours after cardiac arrest (CA) can predict nonsurvival in children. This neuroprognostication tool aids in determining outcomes 12 months post-cardiac arrest.
Area of Science:
- Pediatric critical care medicine
- Neuroscience
- Biomedical engineering
Background:
- Early neuroprognostication in children after cardiac arrest (CA) is challenging.
- Electroencephalography (EEG) is used in adults but requires validation in pediatric populations.
- Machine learning can enhance EEG-based prognostication.
Purpose of the Study:
- To evaluate the predictive value of quantitative EEG (qEEG) features for 12-month survival after CA in children.
- To validate EEG findings using visual analysis of background patterns.
- To apply machine learning for improved neuroprognostication.
Main Methods:
- Retrospective single-center study of children (0-17 years) after CA.
- EEG recordings at 24 hours post-return of circulation (ROC) were analyzed.
- A random forest model was trained using qEEG features; visual classification of background patterns was performed.
Main Results:
- The random forest model predicted 12-month mortality with 0.77 accuracy and 1.0 positive predictive value.
- EEG signal continuity and amplitude were key predictive features.
- No patients with a background pattern other than continuous with amplitudes >20 μV survived 12 months.
Conclusions:
- Quantitative EEG and visual EEG background classification at 24 hours post-ROC are strong predictors of nonsurvival in children after CA.
- These methods offer valuable insights for neuroprognostication in pediatric CA survivors.
Background And Objectives:
Early neuroprognostication in children with reduced consciousness after cardiac arrest (CA) is a major clinical challenge. EEG is frequently used for neuroprognostication in adults, but has not been sufficiently validated for this indication in children. Using machine learning techniques, we studied the predictive value of quantitative EEG (qEEG) features for survival 12 months after CA, based on EEG recordings obtained 24 hours after CA in children. The results were confirmed through visual analysis of EEG background patterns.
Methods:
This is a retrospective single-center study including children (0-17 years) with CA, who were subsequently admitted to the pediatric intensive care unit (PICU) of a tertiary care hospital between 2012 and 2021 after return of circulation (ROC) and were monitored using EEG at 24 hours after ROC. Signal features were extracted from a 30-minute EEG segment 24 hours after CA and used to train a random forest model. The background pattern from the same EEG fragment was visually classified. The primary outcome was survival or death 12 months after CA. Analysis of the prognostic accuracy of the model included calculation of receiver-operating characteristic and predictive values. Feature contribution to the model was analyzed using Shapley values.
Results:
Eighty-six children were included (in-hospital CA 27%, out-of-hospital CA 73%). The median age at CA was 2.6 years; 53 (62%) were male. Mortality at 12 months was 56%; main causes of death on the PICU were withdrawal of life-sustaining therapies because of poor neurologic prognosis (52%) and brain death (31%). The random forest model was able to predict death at 12 months with an accuracy of 0.77 and positive predictive value of 1.0. Continuity and amplitude of the EEG signal were the signal parameters most contributing to the model classification. Visual analysis showed that no patients with a background pattern other than continuous with amplitudes exceeding 20 μV were alive after 12 months.
Discussion:
Both qEEG and visual EEG background classification for registrations obtained 24 hours after ROC form a strong predictor of nonsurvival 12 months after CA in children.
