A study published in peer-reviewed American Journal of Health-System Pharmacy last month found that machine learning and advanced analytics technology can successfully identify instances of drug diversion – a term for when drugs are stolen from healthcare facilities – 160 days faster than traditional, non machine methods. AI can do so even with high volumes of data, unlike its human counterpart who have kept track of the missing drugs until now.
The study came from Atlanta, Georgia-based Invistics, a software company with technology for analyzing and tracking inventory in healthcare systems.
Enhanced Direct Enrollment: Georgia Access and the Power of Partnership
Across the nation, state-based health insurance exchanges are searching for ways to better serve their communities while making enrollment easier, more personal, and more accessible for everyone.
The retrospective study looked at drug diversion at 10 acute-care inpatient hospitals that are part of four health systems in total. The data analyzed included 27.9 million medication movement transactions from nurses, pharmacy, and anesthesia clinicians, spanning over the course of 8 to 24 months.
Thrown into the mix were 22 known drug diversion cases. The study aimed to see if machine learning and analytics technology could not only successfully identify those cases from the 27.9 million, but if machine learning and analytics technology could do so faster than the current standard of detection that originally found these 22 diversions.
Historical methods of diversion detection include looking at monthly usage reports or daily discrepancy reports. However, these standard methods of detection prove problematic on a few fronts. For one, people can hide diversion. And two, any diversion that is detected often is not flagged immediately since the data is reviewed weeks or months after it occurs. Further, hospitals historically rely on clinicians reporting impaired coworkers’ behavior to drive investigation of possible diversion.
The study noted that not only did the machine learning and advanced analytics technology flag the 22 cases of drug diversion, but it did so 160 days before standard methods, on average. Further, the machine learning method technology had a high accuracy rate — 96.3%.
The Power of One: Redefining Healthcare with an AI-Driven Unified Platform
In a landscape where complexity has long been the norm, the power of one lies not just in unification, but in intelligence and automation.
“The findings prove that advances in machine learning and analytics are a real game changer — and can improve the detection of drug diversion in hospitals and other healthcare settings,” says Tom Knight, CEO of Invistics, in a news release. “This is really important, considering the huge financial, clinical, and emotional burden that medication theft imposes on healthcare systems, patients, and families.”
Aside from Invistics, other institutions involved in the study were: Piedmont Athens Regional Medical Center, Scripps Health, Piedmont Healthcare, and EnvisionChange.