Handling Temporality of Clinical Events for Drug Safety Surveillance
2015 (English)In: AMIA Annual Symposium, American Medical Informatics Association , 2015Conference paper (Refereed)Text
Using longitudinal data in electronic health records (EHRs) for post-marketing adverse drug event (ADE) detection allows for monitoring patients throughout their medical history. Machine learning methods have been shown to be efficient and effective in screening health records and detecting ADEs. How best to exploit historical data, as encoded by clinical events in EHRs is, however, not very well understood. In this study, three strategies for handling temporality of clinical events are proposed and evaluated using an EHR database from Stockholm, Sweden. The random forest learning algorithm is applied to predict fourteen ADEs using clinical events collected from different lengths of patient history. The results show that, in general, including longer patient history leads to improved predictive performance, and that assigning weights to events according to time distance from the ADE yields the biggest improvement.
Place, publisher, year, edition, pages
American Medical Informatics Association , 2015.
drug safety surveillance, pharmacovigilance, adverse drug events, electronic health records, temporality, predictive modeling
Research subject Computer and Systems Sciences
IdentifiersURN: urn:nbn:se:su:diva-123950OAI: oai:DiVA.org:su-123950DiVA: diva2:878594