Related Experiment Video
Updated: Oct 26, 2025
Author Spotlight: Advancing Pediatric Epilepsy Surgery in Children Through Novel Biomarkers and Enhanced Localization
Published on: September 20, 2024
Development and Evaluation of Computable Phenotypes in Pediatric Epilepsy:3 Cases
Sabrina Pan1, Alan Wu1, Mark Weiner1
1Department of Population Health Sciences, Weill Cornell Medicine/New York-Presbyterian Hospital, New York, NY, USA.
Insights
Accurate computable phenotypes for pediatric epilepsy research are feasible for hypoxic-ischemic encephalopathy but challenging for juvenile myoclonic epilepsy. These findings highlight data limitations in identifying specific patient cohorts for epilepsy studies.
Area of Science:
- Medical Informatics
- Pediatric Neurology
- Epilepsy Research
Background:
- Electronic health records (EHRs) enable computable phenotype development for patient cohort identification.
- The accuracy of diagnostic codes for key pediatric epilepsy concepts is largely unknown.
- Important concepts include risk factors (e.g., neonatal hypoxic-ischemic encephalopathy), treatment resistance, and epilepsy syndromes (e.g., juvenile myoclonic epilepsy).
Purpose of the Study:
- To develop and evaluate computable phenotypes for specific pediatric epilepsy conditions using EHR data.
- To assess the accuracy of these phenotypes in identifying well-defined patient cohorts.
Main Methods:
- Gold standard cohorts were established for neonatal hypoxic-ischemic encephalopathy, treatment-resistant epilepsy, and juvenile myoclonic epilepsy.
- Diagnostic and procedure codes were extracted from EHRs for children with epilepsy or seizures.
- Phenotype performance was evaluated using sensitivity, positive predictive value, and F-measure.
Main Results:
- A computable phenotype for neonatal hypoxic-ischemic encephalopathy achieved high accuracy (F-measure 0.98).
- A phenotype for treatment-resistant epilepsy showed moderate accuracy (F-measure 0.77).
- A phenotype for juvenile myoclonic epilepsy had high positive predictive value but low sensitivity (F-measure 0.66).
Conclusions:
- Computable phenotype accuracy varies significantly across different pediatric epilepsy concepts.
- High accuracy was achieved for hypoxic-ischemic encephalopathy, moderate for treatment resistance, and low for juvenile myoclonic epilepsy.
- This heterogeneity underscores challenges in using administrative data for pediatric epilepsy research cohort identification.
Introduction:
Computable phenotypes allow identification of well-defined patient cohorts from electronic health record data. Little is known about the accuracy of diagnostic codes for important clinical concepts in pediatric epilepsy, such as (1) risk factors like neonatal hypoxic-ischemic encephalopathy; (2) clinical concepts like treatment resistance; (3) and syndromes like juvenile myoclonic epilepsy. We developed and evaluated the performance of computable phenotypes for these examples using electronic health record data at one center.
Methods:
We identified gold standard cohorts for neonatal hypoxic-ischemic encephalopathy, pediatric treatment-resistant epilepsy, and juvenile myoclonic epilepsy via existing registries and review of clinical notes. From the electronic health record, we extracted diagnostic and procedure codes for all children with a diagnosis of epilepsy and seizures. We used these codes to develop computable phenotypes and evaluated by sensitivity, positive predictive value, and the F-measure.
Results:
For neonatal hypoxic-ischemic encephalopathy, the best-performing computable phenotype (HIE ICD-9/10 and [brain magnetic resonance imaging (MRI) or electroencephalography (EEG) within 120 days of life] and absence of commonly miscoded conditions) had high sensitivity (95.7%, 95% confidence interval [CI] 85-99), positive predictive value (100%, 95% CI 95-100), and F measure (0.98). For treatment-resistant epilepsy, the best-performing computable phenotype (3 or more antiseizure medicines in the last 2 years or treatment-resistant ICD-10) had a sensitivity of 86.9% (95% CI 79-93), positive predictive value of 69.6% (95% CI 60-79), and F-measure of 0.77. For juvenile myoclonic epilepsy, the best performing computable phenotype (JME ICD-10) had poor sensitivity (52%, 95% CI 43-60) but high positive predictive value (90.4%, 95% CI 81-96); the F measure was 0.66.
Conclusion:
The variable accuracy of our computable phenotypes (hypoxic-ischemic encephalopathy high, treatment resistance medium, and juvenile myoclonic epilepsy low) demonstrates the heterogeneity of success using administrative data to identify cohorts important for pediatric epilepsy research.
More Related Videos
Related Concept Videos
01:24Epilepsy and Seizures: Overview
Various factors can trigger epilepsy, including genetic factors, brain damage, metabolic causes, and unknown etiology. Diagnosis of epilepsy involves electroencephalography (EEG), which...
01:13Seizures: Classification
Seizures are typically classified into two main categories: focal and generalized seizures.
Focal Seizures
Focal seizures originate from specific regions of the brain. These seizures are further sub-classified into two types: