Share

2021–22 Olin Brookings Commission Report

Download a copy of the full report by the 2021–22 Olin Brookings Commission, “Tackling the US Opioid Crisis: A data-driven solution and policy recommendations.” The report, presented April 27, 2022, at the Brookings Institution in Washington, DC, explains a newly developed AI-powered anomaly detection tool to thwart opioid diversion, the rationale behinds its policy recommendations and the context for the work. Download the report

Olin Brookings Commission

  • Tackling the opioid epidemic

The Olin Brookings Commission—Driving Quality of Life

The Olin Brookings Commission is a multiyear initiative, underwritten by The Bellwether Foundation Inc., that convenes world-class WashU Olin Business School faculty, Brookings Institution scholars and industry leaders to explore issues of global significance. Each year, a new commission will direct research and gather data to examine megatrend topics that affect the quality of life in our community. Each commission’s work culminates with a report to national, regional and local decision-makers, summarizing its conclusions and recommending business strategies and policy measures designed to drive tangible impact on the world.

The 2021–22 Olin Brookings Commission

Inaugural commission develops strategies, recommendations for curbing the opioid epidemic.

video According to some reports, more than 100 billion prescription hydrocodone and oxycodone pills were distributed in the United States between 2006 to 2014. A staggering percentage of suspicious opioid transactions has fueled a long-lasting epidemic of opioid dependency and death. In 2020 alone, approximately 69,700 people died of overdoses involving opioids in the United States.

In the first of three projects by the Olin Brookings Commission, researchers and commission members aimed to tackle the opioid epidemic and, specifically, the patterns of diversion within the drug supply chain that have fueled costly and deadly patterns of opioid dependence and death in communities across the country.

In collaboration with Olin’s Center for Analytics and Business Insights, the research team tapped into advances in data collection, data mining, artificial intelligence and machine learning to tackle the problem. The solution: Olin researchers developed a suite of anomaly detection tools to identify diversion trends in data submitted to a database maintained by the US 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 buyers, researchers developed a tool to flag and stop fraudulent opioid shipments before they are diverted. The team identified patterns among likely diverters and tested their findings against a known database of convicted buyers.

The tool is designed to flag future diverters with 100% precision accuracy (i.e., if the tool flags a buyer as a diverter, it is almost guaranteed that the prediction is correct). In other words, the tool will not produce false positives. The team achieved that level of precision accuracy because the tool “lives with” a moderate degree (51%) of recall accuracy (i.e., the tool catches about one-in-two diverters). In other words, the tool will result in many false negatives.

Download the 2021–22 commission report

Questions or feedback?
Send us an email.

Retrieving Data

The Commission’s Opioid Policy Recommendations

Through its work, the 2021–22 Olin Brookings Commission developed a series of policy recommendations that, in combination, can overcome existing policy obstacles to empower industry and government to implement the team’s near real-time detection and alert system to thwart opioid diversion in the supply chain.

  • Establish a daily or near-real-time pilot for integration of anomaly detection tool to test the operational methods.
  • Modernize ARCOS technology infrastructure to support daily or near-real-time data entry by registrants.
  • Update the law to require the annual release of ARCOS data to technology stakeholders for the purpose of testing and refining artificial intelligence and machine learning tools and revalidate initial findings with five years’ worth of the most recently available data. Provide for daily or near-real-time access in order to support the pilot (referenced earlier).
  • Require the sharing of flagged data across federal agencies to include agencies with antidiversion policy or law enforcement efforts, to include but not limited to the Office of National Drug Control Policy (ONDCP), US Attorney Offices and High Intensity Drug Trafficking Areas (HIDTA).
  • Update the law to require electronic reporting by all DEA registrants.
  • Ensure competency for DEA professionals in artificial intelligence/machine learning or data science through workforce development and/or recruiting to support investigations within the agency.
  • Encourage existing DEA investigators within the Diversion Control Division to receive training to effectively read and analyze spreadsheets, analyze statistics and develop statistical models of ARCOS data.
  • Enter into an interagency agreement with National Institute of Standards and Technology (NIST) to utilize its artificial intelligence/machine learning experts until the DEA acquires sufficient in-house expertise to drive the application of data science anomaly detection of illicit opioid trafficking.
  • Identify an independent party—working in conjunction with the DEA—to leverage data captured from the tool for analysis and alerting industry of suspicious actors or transactions in the supply chain.
  • Appropriate funding from the registration and reregistration fees to cover the cost of upgrading and maintaining the ARCOS infrastructure, including adequate data storage.
  • Appropriate such funding as needed for recruiting and talent development as proposed in recommendations 6 and 7.
  • Publish a notice in the Federal Register to solicit comments from the law enforcement community and industry’s compliance component on response guidance for suspicious flags.
  • Establish an industry advisory group made up of manufacturers, distributors, importers, exporters, hospitals and retailers to meet quarterly, and obtain industry perspective and collaboration.
  • Require DEA to report annually to Congress on the capturing, monitoring and action on ARCOS data, as well as technology challenges, with a focus on evaluating the efficacy of the artificial intelligence/machine-learning-driven solution. Include industry concerns and recommendations, as provided by the industry advisory group. Share the annual report with other federal, local, state and industry stakeholders.

Inaugural Commission Members

Anthony Sardella The Hon. Mary Bono Dr. Ann Marie Dale Van Ingram Gina Papush Darrell M. West
  • Anthony Sardella, founder, evolve24; faculty member, WashU Olin Business School. Commission chair.
  • The Hon. Mary Bono, board member, Community Anti-Drug Coalitions of America; former US representative.
  • Dr. Ann Marie Dale, professor of medicine and occupational therapy, Washington University School of Medicine.
  • Van Ingram, executive director, Kentucky Office of Drug Control.
  • Gina Papush, formerly global chief data and analytics officer, Cigna.
  • Darrell M. West, vice president and director, Governance Studies; senior fellow, Center for Technology Innovation, Brookings.

Project Milestones

  • April 27, 2022. The Olin Brookings Commission presented its research and policy recommendations to industry representatives, law enforcement and medical professionals, and policymakers at the Brookings Institution.
  • November 2021. The research team submitted its work developing an AI-driven “anomaly detection tool” designed to flag potential diverters of opioid shipments to the Journal of Marketing for review.
  • August 19, 2021. The second commission meeting on the opioids crisis reviews research progress and offers further direction.
  • August 16, 2021. The team from Olin’s Center for Analytics and Business Insights reports update on machine learning efforts to flag suspicious opioid transactions. Read more.
  • May 12, 2021. The first meeting of the inaugural Olin Brookings Commission.

Commission News Updates

Follow our news feed here

Leading the Research

Seethu Seetharaman Michael Wall Luoyexin (Annie) Shi Chenthuran Abeyakaran

Seethu Seetharaman, academic director of Olin’s Center for Analytics and Business Insights, will lead the research effort with support from Michael Wall, professor of practice and CABI co-director, along with PhD candidate Luoyexin (Annie) Shi and Chenthuran Abeyakaran, a master’s degree student in data analytics and statistics at WashU who received his bachelor's degree in computer science and applied math in 2021.

Project Timeline

Project Timeline

Research Findings

A CABI analysis of 400 million opioid transactions between 2006 and 2012 found:

  • Opioid purchase levels: Legitimate buyers purchase lower levels of opioids on a per-unit basis; their behaviors are very similar to each other and the amounts they purchase over time are consistent.
  • Purchase frequency: Legitimate buyers purchase lower levels of opioids on a per-unit basis; their purchase amounts are consistent over time and buyers look very similar to each other.
  • Population density: Legitimate buyers purchase lower levels of opioids on a per-unit basis per day and per person. Again, purchase amounts are consistent over time, and buyers look very similar to each other.

Partners

WashU Olin Business School logo