Optimizing EEG monitoring in critically ill children at risk for electroencephalographic seizures
Kyle Coleman1, France W Fung2, Alexis Topjian3
1Department of Biostatistics, Epidemiology and Informatics, University of Pennsylvania Perelman School of Medicine, United States.
Insights
A new multi-stage prediction model efficiently guides continuous EEG monitoring (CEEG) for electroencephalographic seizure (ES) detection in critically ill children, reducing CEEG use and optimizing resource allocation.
Area of Science:
- Pediatric Neurology
- Critical Care Medicine
- Biomedical Engineering
Background:
- Continuous EEG monitoring (CEEG) is crucial for identifying electroencephalographic seizures (ES) in critically ill children.
- Resource limitations necessitate optimized strategies for CEEG deployment and ES detection.
- Clinical and electroencephalographic (EEG) covariates are vital for predicting ES risk.
Purpose of the Study:
- To develop an efficient multi-stage prediction model for guiding CEEG utilization in critically ill children.
- To identify electroencephalographic seizures (ES) more effectively using clinical and EEG data.
- To optimize the allocation of limited CEEG resources.
Main Methods:
- Analysis of a prospective single-center cohort of 1399 children undergoing CEEG.
- Development and training of a four-stage prediction model using logistic regression, elastic net, random forest, and CatBoost.
- Evaluation of candidate models using cross-validation to construct an optimal multi-stage model.
Main Results:
- The optimal multi-stage model achieved a cumulative specificity of 0.197 and a cumulative F1 score of 0.326.
- Maintained a high minimum cumulative sensitivity of 0.938, with 11% of subjects with ES falsely classified as low-risk.
- Potential to reduce CEEG utilization by 32% and 47% compared to fixed 24-hour or 48-hour monitoring periods.
- A web application, EEGLE (EEG Length Estimator), was developed for model implementation.
Conclusions:
- The multi-stage prediction model can reduce CEEG utilization in patients with a lower risk of ES.
- Facilitates CEEG resource reallocation towards patients identified as higher risk for ES.
- Enables more efficient and targeted use of continuous EEG monitoring in pediatric critical care.
Objective:
Strategies are needed to optimally deploy continuous EEG monitoring (CEEG) for electroencephalographic seizure (ES) identification and management due to resource limitations. We aimed to construct an efficient multi-stage prediction model guiding CEEG utilization to identify ES in critically ill children using clinical and EEG covariates.
Methods:
The largest prospective single-center cohort of 1399 consecutive children undergoing CEEG was analyzed. A four-stage model was developed and trained to predict whether a subject required additional CEEG at the conclusion of each stage given their risk of ES. Logistic regression, elastic net, random forest, and CatBoost served as candidate methods for each stage and were evaluated using cross validation. An optimal multi-stage model consisting of the top-performing stage-specific models was constructed.
Results:
When evaluated on a test set, the optimal multi-stage model achieved a cumulative specificity of 0.197 and cumulative F1 score of 0.326 while maintaining a high minimum cumulative sensitivity of 0.938. Overall, 11 % of test subjects with ES were removed from the model due to a predicted low risk of ES (falsely negative subjects). CEEG utilization would be reduced by 32 % and 47 % compared to performing 24 and 48 h of CEEG in all test subjects, respectively. We developed a web application called EEGLE (EEG Length Estimator) that enables straightforward implementation of the model.
Conclusions:
Application of the optimal multi-stage ES prediction model could either reduce CEEG utilization for patients at lower risk of ES or promote CEEG resource reallocation to patients at higher risk for ES.
