Ways to deal with the opioid crisis

The opioid epidemic has decimated many communities across the country. It has cost lives, injured families and disrupted the social fabric of many places. Approximately 69,700 people lost their lives in 2020 due to opioid abuse in the United States.

To address this crisis, researchers at Washington University Olin School of Business spent a year studying the issue and developing recommendations to mitigate the outbreak. In front of an audience of policy makers, journalists, scientists and health professionals, these individuals and members of the Olin Brookings Commission presented their solutions and recommendations to tackle the troubling aspects of the opioid epidemic.

The six-member commission has met several times over the past 12 months and recently issued a 53-page overview of the research process, policy recommendations and background– at an event in Brookings. The presentation described AI-based tools to curb the misdirection of opioid shipments and the design of policy recommendations to facilitate the use of these tools.

“Listening to the presentation, I have this sick feeling in my stomach, thinking that if we had had these tools 10 years ago, how many lives could we have saved?” said Van Ingram, one of the Olin Brookings Commission members and executive director of the Kentucky Office of Drug Control.

The group was the first convened by WashU Olin as part of a partnership with Brookings underwritten by The Bellwether Foundation. The project was designed to explore quality of life issues in communities and recommend policy changes to address them.

Focus on prescription drug diversion

The report tackled the opioid epidemic and, more specifically, the illicit diversion of prescription opioids that has exploited distribution supply chain blind spots, fueling decades of addiction and death. Once the researchers focused on a data-driven answer to this problem, the six-member commission devised a series of policy recommendations to make them easier to use.

“Blind spots still exist,” said Anthony Sardella, chairman of the commission and member of the research team. “Our goal: can you use data science to remove these blind spots? It is with this objective that our research began. (See the complete list of members of the Olin Brookings Commission 2021-22 on the committee’s website.) According to some reportsover 100 billion prescription hydrocodone and oxycodone pills were dispensed in the United States between 2006 and 2014.

An AI-based solution

Olin researchers from the school’s Center for Analytics and Business Insights focused on patterns of diversion within the drug supply chain using advances in data collection, data mining , artificial intelligence and machine learning. The Solution: Olin researchers developed a suite of anomaly detection tools to identify misuse patterns in data submitted to a database maintained by the United States Drug Enforcement Administration.

Using historical data from the Automation of Reports and Consolidated Orders System (ARCOS) database from 2006 to 2012, including more than 400 million opioid transactions and 277,000 purchasers, researchers developed a tool to report and stop fraudulent opioid shipments before they are diverted. The team identified patterns among the likely hijackers and tested their findings against a known database of convicted buyers.

The tool is designed to flag future hijackers with 100% accuracy (i.e. if the tool flags a buyer as a hijacker, the prediction is almost guaranteed to be correct). In other words, the tool will not produce false positives. The team achieved this level of accuracy because the tool “lives with” a moderate degree (51%) of recall accuracy (i.e. the tool detects approximately one in two deviators). In other words, the team was willing to live with a higher rate of false negatives to ensure 100% accuracy in flagging likely hijackers.

Values-based and data-driven work

“This work is emblematic of what WashU Olin Business School stands for,” said Mark P. Taylor, the Olin dean who initiated the work to secure the Bellwether grant. “We are committed to applying the rigorous use of data and careful consideration of our principles to go beyond the bottom line, to address and impact critical issues in society.”

Once the research team locked down their anomaly detection tool, the 2021–22 Olin Brookings Commission has developed a series of policy recommendations which, when combined, can overcome existing policy barriers to enable industry and government to work together and implement the team’s near real-time detection and alerting system to counter the diversion of opioids in the supply chain.

The 14 recommendations include implementing a daily or near real-time pilot for anomaly detection tool integration to test operational methods and modernizing the ARCOS technology infrastructure to support daily or near real-time data entry by reporters. And the job is not done. The research team intends to refine their model to potentially look for additional indicators, and even techniques to signal the movement of over-the-counter opioids.

“We can determine whether a transaction is supposed to happen or not,” said Annie Shi, research team member and doctoral student in marketing at WashU. “For example, if DEA receives a new transaction request, our model will be able to predict whether that transaction is supposed to happen or not. If it is expected to be suspicious, the DEA may hold that shipment until further action is taken.

Leave a Comment