New data-driven method to predict the therapeutic indication of redeemed prescriptions in secondary data sources: a case study on antiseizure medications users aged ≥65 identified in Danish registries

OBJECTIVES: We aimed to develop a new data-driven method to predict the therapeutic indication of redeemed prescriptions in secondary data sources using antiepileptic drugs among individuals aged ≥65 identified in Danish registries. DESIGN: This was an incident new-user register-based cohort study using Danish registers. SETTING: The study setting was Denmark and the study period was 2005-2017. PARTICIPANTS: Participants included antiepileptic drug users in Denmark aged ≥65 with a confirmed diagnosis of epilepsy. PRIMARY AND SECONDARY OUTCOME MEASURES: Sensitivity served as the performance measure of the algorithm. RESULTS: The study population comprised 8609 incident new users of antiepileptic drugs. The sensitivity of the algorithm in correctly predicting the therapeutic indication of antiepileptic drugs in the study population was 65.3% (95% CI 64.4 to 66.2). CONCLUSIONS: The algorithm demonstrated promising properties in terms of overall sensitivity for predicting the therapeutic indication of redeemed antiepileptic drugs by older individuals with epilepsy, correctly identifying the therapeutic indication for 6 out of 10 individuals using antiepileptic drugs for epilepsy.