Abstract
BACKGROUND AND OBJECTIVES: Genetic testing in epilepsy has become increasingly available, and recommendations for its use have been set forth by professional society guidelines. The development of a user-friendly risk prediction model may aid providers in selecting adult patients with a high likelihood of receiving a positive genetic test result.
METHODS: Adults who underwent multigene panel testing for epilepsy from March 2016 to June 2024 were divided into a training (n = 1449) and a testing set (n = 1450). We developed prediction models based on clinical characteristics using logistic regression and FasterRisk scores for positive genetic tests and evaluated their performance.
RESULTS: The prediction models had poor discriminative power and failed to predict positive results, suggesting that conventional clinical characteristics (sex, intellectual disability, developmental delay, autism, medically refractory epilepsy, family history of epilepsy, and age at seizure onset) are insufficient for selecting patients for genetic testing.
DISCUSSION: Our findings suggest that routine genetic testing may be broadly warranted for adults with unexplained epilepsy, as clinical characteristics alone appear unable to reliably identify which patients are likely to have positive results on multigene panels. Future models may benefit from incorporating physical exam findings, neuroimaging, and electroencephalogram data, as well as larger training sets.