Detecting drug diversion in health-system data using machine learning and advanced analytics

Abstract

Disclaimer In an effort to expedite the publication of articles related to the COVID-19 pandemic, AJHP is posting these manuscripts online as soon as possible after acceptance. Accepted manuscripts have been peer-reviewed and copyedited, but are posted online before technical formatting and author proofing. These manuscripts are not the final version of record and will be replaced with the final article (formatted per AJHP style and proofed by the authors) at a later time. Purpose The theft of drugs from healthcare facilities, also known as drug diversion, occurs frequently but is often undetected. This paper describes a research study to develop and test novel drug diversion detection methods. Improved diversion detection and reduction in diversion improves patient safety, limits harm to the person diverting, reduces the public health impact of substance use disorder, and mitigates significant liability risk to pharmacists and their organizations. Methods Ten acute care inpatient hospitals across 4 independent health systems extracted 2 datasets from various health information technology systems. Both datasets were consolidated, normalized, classified, and sampled to provide a harmonious dataset for analysis. Supervised machine learning methods were iteratively used on the initial sample dataset to train algorithms to classify medication movement transactions as involving a low or high risk of diversion. Thereafter, the resulting machine learning model classified the risk of diversion in a historical dataset capturing 8 to 24 months of history that included 27.9 million medication movement transactions by 19,037 nursing, 1,047 pharmacy, and 712 anesthesia clinicians and that included 22 known, blinded diversion cases to measure when the model would have detected the diversion compared to when the diversion was actually detected by existing methods. Results The machine learning model had 95.9% specificity and 96.6% sensitivity in detecting transactions involving a high risk of diversion using the initial sample dataset. In subsequent testing using the much larger historical dataset, the analytics detected known diversion cases (n = 22) in blinded data faster than existing detection methods (a mean of 160 days and a median of 74 days faster; range, 7-579 days faster). Conclusion The study showed that (1) consolidated datasets and (2) supervised machine learning can detect known diversion cases faster than existing detection methods. Users of the technology also noted improved investigation efficiency.

Role of artificial intelligence in pharmacy practice: A narrative review

“…The linking of indications to medication orders would be able to help pharmacist better determine appropriate medication and dosing, an initiative that is supported by a patient survey 37,38 . An additional aspect that has been evaluated in the literature is the use of AI to prevent diversion of controlled substances, which is supported by guidelines and a multicenter study which found an accurate algorithm identifying cases of diversion a median of 74 days faster than existing methods 39,40 . Another area that AI can help optimize is the ability to predict medication demand and streamline inventory management, reducing the risk of medication shortages, although external factors will always need to be considered.…”

“…37,38 An additional aspect that has been evaluated the literature is the use of AI to prevent diversion of controlled substances, which is supported by guidelines and a multicenter study which found an accurate algorithm identifying cases of diversion a median of 74 days faster than existing methods. 39,40 Another area that AI can help optimize is the ability to predict medication demand and streamline inventory management, reducing the risk of medication shortages, although external factors will always need to be considered. An example of the role of AI throughout the medication use process can be found in Figure 2…”

Perioperative Opioid Usage Monitoring and Waste

“…Flowlytics ® from Invistics was developed using artificial intelligence (AI) to monitor opioid usage and to detect potential diversion. A recent study indicated that use of machine learning and advanced analytics can detect known diversion cases much faster (ranges from 7–579 days faster) than traditional diversion detection methods that use periodic reporting [ 4 ]. This new methodology has demonstrated more than 95% accuracy, specificity, and sensitivity, and is designed to alert investigators for potential drug diversion by quickly detecting: 1) Lack of or discrepancy in drug reconciliation, 2) Time-range matrix to detect significant differences in drug waste behavior from a particular provider as compared to peers in similar cases and 3) A pattern of full dose wasting where a full vial of unused medication goes into waste instead of being returned [ 5 ].…”

Prevention of drug diversion and substance use disorders among anesthesiologists: a narrative review

“… 42 The use of health-system data coupled with machine learning and advanced analytics has been shown to be highly accurate in detecting transactions involving a high risk of diversion. 43 Machine learning detected diversion an average of 160 days (median 74 days) faster.…”

“… 51 Darbishire et al reported testing in pharmacy students detected 2.2 events per 100 students annually. 43 …”