Meaningful Drug Interaction Alerts (Utah)

This project does not have any related annual summary.
This project does not have any related event.
This project does not have any related resource.
This project does not have any related survey.
This project does not have any related project spotlight.
This project does not have any related survey.
This project does not have any related story.
This project does not have any related emerging lesson.

Project Details - Ongoing


Drug-drug interactions (DDIs) are responsible for up to 14 percent of adverse drug reactions in hospitalized patients, are a major risk factor for hospitalization, and occur in up to 13 percent of elderly ambulatory patients. DDIs continue to occur despite the widespread use of clinical decision support (CDS) systems. These systems trigger alerts for drug pairs that potentially interact in a patient’s medication regimen. This simplistic approach does not utilize contextual, patient-specific data and results in clinically irrelevant alerts. Some reports indicate that over 90 percent of DDI alerts seen by prescribers are overridden, resulting in alert fatigue. By adding patient context via DDI alert algorithms, clinically irrelevant alerts would be reduced, with a reduction of alert fatigue and improvement in patient safety.

This project intends to change the underlying framework for DDI alerting to an advanced and contextual CDS by 1) using new and existing evidence related to exposure to DDIs to inform CDS, 2) constructing and validating alert algorithms that incorporate relevant drug attributes and patient characteristics, and 3) widely implementing and evaluating alerting algorithms across the healthcare system. Partnering with experts in drug interactions and biomedical informatics will inform the process with the end goal of safer healthcare delivery. Additionally, researchers hypothesize that the approach will improve the specificity of alerts, highlight drug combinations that should not be administered, and allow for end-user feedback to individualize alerts, while ensuring that patient safety is not compromised.

The specific aims of this project are as follows:

  • Design sharable evidence-based individualized DDI algorithms that capitalize on the wealth of patient data located within electronic health records.
  • Validate the function of newly designed DDI algorithms using electronic health record data. 
  • Conduct a prospective evaluation of DDI algorithms in a variety of healthcare environments, including ambulatory and institutional settings. 

The expected results of this work will identify patients most at risk of harm from DDIs to substantially reduce medication-related adverse drug events, improve quality of care, and reduce health costs. This project may also help CDS systems reach their full potential with respect to DDIs, providing the right information to clinicians at the right time.