Description
Abstract: Clinical decision support (CDS) for drug-drug interactions (DDIs) is often overridden or ignored because of a lack relevance to the patient’s clinical situation. We present 8 contextualized DDI CDS algorithms that use data available in electronic health records to increase specificity while retaining sensitivity. Document-based and computable knowledge artifacts were developed for all 8 DDIs. The computable artifacts were validated using synthetic patient data and then tested using retrospective data from a single urban hospital.
Describe the new knowledge and additional skills the participant will gain after attending your presentation.: The attendee will be able to test contextualized drug-drug interaction algorithms designed to permit healthcare providers, organizations, and systems to implement useful decision support to reduce patient harm.
Authors:
Richard Boyce (Presenter)
University of Pittsburgh
Eric Chou, University of Pittsburgh
Baran Balkan, University of Arizona
Andrew Romero, University of Arizona
Philip Hansten, University of Washington
John Horn, University of Washington
Vignesh Subbian, University of Arizona
Sheila Gephart, University of Arizona
Daniel Malone, University of Utah