AUTHOR=Breitenstein Peter Suhr , Mahmoud Israa , Al-Azzawi Fahed , Shakibfar Saeed , Sessa Maurizio 

TITLE=A machine-learning guided method for predicting add-on and switch in secondary data sources: A case study on anti-seizure medications in Danish registries

JOURNAL=Frontiers in Pharmacology

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/pharmacology/articles/10.3389/fphar.2022.954393

DOI=10.3389/fphar.2022.954393

ISSN=1663-9812

ABSTRACT=Purpose: There is a lack of available evidence regarding the treatment pattern of switches and add-ons for individuals aged 65 or older with epilepsy during the first years from the time they received their first antiseizure medication because of the lack of valid methods. Therefore, this study aimed to develop an algorithm for identifying switches and add-ons using secondary data sources for antiseizure medication users. 

Methods: Danish nationwide databases were used as data sources. Residents in Denmark between 1996 and 2018 who were diagnosed with epilepsy and redeemed their first prescription for antiseizure medication after epilepsy diagnosis were followed for 730 days until the end of the follow-up period, death, or emigration to assess switches and add-ons occurred during the follow-up period. The study outcomes were the overall accuracy of classification of switch or add-on of the newly developed algorithm.

Results: In total, 15870 individuals were included in the study population with a median age of 72.9 years, of who 52.0 % were male and 48.0% were female. 988 of the 15879 patients from the study population underwent during the 730-days follow-up period, 988 individuals (6.2%) underwent a total of 1485 medication events with co-exposure to 2 or more antiseizure medications. The newly developed algorithmic method correctly identified 9 out of 10 add-ons (overall accuracy 92 %) and 9 out of 10 switches (overall accuracy 88 %). 

Conclusion: The majority of switches and add-on occurred early during the first 2 years of disease and according to clinical recommendations. The newly developed algorithm correctly identified 9 out of 10 switches/add-ons.