Development and validation of machine learning models for prediction of seizure outcome after pediatric epilepsy surgery
Abstract
Objective: There is substantial variability in reported seizure outcome following pediatric epilepsy surgery, and lack of individualized predictive tools that could evaluate the probability of seizure freedom postsurgery. The aim of this study was to develop and validate a supervised machine learning (ML) model for predicting seizure freedom after pediatric epilepsy surgery.Methods: This is a multicenter retrospective study of children who underwent epilepsy surgery at five pediatric epilepsy centers in North America. Clinical information, diagnostic investigations, and surgical characteristics were collected, and used as features to predict seizure‐free outcome 1 year after surgery. The dataset was split randomly into 80% training and 20% testing data. Thirty‐five combinations of five feature sets with seven ML classifiers were assessed on the training cohort using 10‐fold cross‐validation for model development. The performance of the optimal combination of ML classifier and feature set was evaluated in the testing cohort, and compared with logistic regression, a classical statistical approach.Results: Of the 801 patients included, 61.3% were seizure‐free 1 year postsurgery. During model development, the best combination was XGBoost ML algorithm with five features from the univariate feature set, including number of antiseizure medications, magnetic resonance imaging lesion, age at seizure onset, video‐electroencephalography concordance, and surgery type, with a mean area under the curve (AUC) of .73 (95% confidence interval [CI] = .69–.77). The combination of XGBoost and univariate feature set was then evaluated on the testing cohort and achieved an AUC of .74 (95% CI = .66–.82; sensitivity = .87, 95% CI = .81–.94; specificity = .58, 95% CI = .47–.71). The XGBoost model outperformed the logistic regression model (AUC = .72, 95% CI = .63–.80; sensitivity = .72, 95% CI = .63–.82; specificity = .66, 95% CI = .53–.77) in the testing cohort (p = .005).Significance: This study identified important features and validated an ML algorithm, XGBoost, for predicting the probability of seizure freedom after pediatric epilepsy surgery. Improved prognostication of epilepsy surgery is critical for presurgical counseling and will inform treatment decisions.Keywords
This publication has 38 references indexed in Scilit:
- Comparison of imputation methods for missing laboratory data in medicineBMJ Open, 2013
- Machine Learning Approach for the Outcome Prediction of Temporal Lobe Epilepsy SurgeryPLOS ONE, 2013
- Definition of drug resistant epilepsy: Consensus proposal by the ad hoc Task Force of the ILAE Commission on Therapeutic StrategiesEpilepsia, 2010
- Research electronic data capture (REDCap)—A metadata-driven methodology and workflow process for providing translational research informatics supportJournal of Biomedical Informatics, 2009
- Outcome predictors for surgical treatment of temporal lobe epilepsy with hippocampal sclerosisEpilepsia, 2008
- The contribution of 18F-FDG PET in preoperative epilepsy surgery evaluation for patients with temporal lobe epilepsySeizure: European Journal of Epilepsy, 2007
- Epilepsy Surgery in Children: Results and Predictors of Outcome on SeizuresEpilepsia, 2007
- Predictors of epilepsy surgery outcome: a meta-analysisEpilepsy Research, 2004
- 10.1162/153244303322753616Applied Physics Letters, 2000
- Neural network analysis of preoperative variables and outcome in epilepsy surgeryJournal of Neurosurgery, 1999