The study compared using these technologies against traditional means of detection, such as monthly anomalous usage reports in 10 acute-care inpatient hospitals across four independent health systems.
The advanced analytics and machine learning technologies detected known diversion cases in blinded data an average of 160 days faster than existing, non-machine learning detection methods. Additionally, the machine learning model demonstrated 96.3% accuracy, 95.9% specificity, and 96.6% sensitivity in detecting transactions at high risk of diversion in the dataset.
Join contributing authors Tom Knight and Pam Letzkus in a panel discussion on the results of the retrospective study detailing the key benefits of using technology to improve drug diversion detection and investigation.
What you can expect to learn
- How hospitals and other healthcare facilities can consolidate data from existing IT systems to detect drug diversion.
- How machine learning can detect drug diversion faster than traditional methods.
