Predicting Adverse Drug Events with Confidence
2015 (English)In: 13 th Scandinavian Conference on Artificial Intelligence: SKAI 2015 / [ed] S. Nowaczyk, IOS Press, 2015, 88-97 p.Conference paper (Refereed)Text
This study introduces the conformal prediction framework to the task of predicting the presence of adverse drug events in electronic health records with an associated measure of statistically valid confidence. The imbalanced nature of the problem was addressed both by evaluating different machine learning algorithms, and by comparing different types of conformal predictors. A novel solution was also evaluated, where different underlying models, each model optimized towards one particular class, were combined into a single conformal predictor. This novel solution proved to be superior to previously existing approaches.
Place, publisher, year, edition, pages
IOS Press, 2015. 88-97 p.
, Frontiers in Artificial Intelligence and Applications, 278
Research subject Computer and Systems Sciences
IdentifiersURN: urn:nbn:se:su:diva-123964DOI: 10.3233/978-1-61499-589-0-88ISBN: 978-1-61499-589-0OAI: oai:DiVA.org:su-123964DiVA: diva2:878608
13 th Scandinavian Conference on Artificial Intelligence