Development and Evaluation of Computable Phenotypes in Pediatric Epilepsy:3 Cases

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.