AI Model Boosts Opioid Treatment Access, Equity

Institute for Operations Research and the Management Sciences

New Study Key Takeaways:

  • New model focuses on more equity and accessibility in opioid overdose treatment locations and resource allocation.
  • Utilizing this model, the results project that within 2 years, there will be a decrease in the number of people with opioid use disorder, an increase in the number of people getting treatment and a decrease in opioid-related deaths.
  • Policymakers should target adding treatment facilities to counties that have significantly fewer facilities than their population share and are more socially vulnerable.

BALTIMORE, MD, October 15, 2024 – The opioid epidemic is a crisis that has plagued the United States for decades. One central issue of the epidemic is inequitable access to treatment for opioid use disorder (OUD), which puts certain populations at a higher risk of opioid overdose.

New research in the INFORMS journal Manufacturing & Service Operations Management provides socioeconomically equitable solutions by utilizing artificial intelligence (AI) and optimization. It's the first research of its kind to target the opioid crisis and identify solutions on a state-by-state level.

"Our proposed solution focuses on equitability and access to treatment facilities based on state data. We found that applying the recommendations from our integrated AI and optimization approach, on average, could decrease the number of people with opioid use disorder (OUD), increase the number of people getting treatment and decrease the number of opioid-related deaths within 2 years," says Joyce Luo of the Massachusetts Institute of Technology.

The study, "Frontiers in Operations: Equitable Data-Driven Facility Location and Resource Allocation to Fight the Opioid Epidemic," was conducted by Luo alongside Bartolomeo Stellato of Princeton University.

"Our recommendations consider how socially vulnerable each county is within a state, which is important to ensure greater socioeconomic equitability for the allocation of facilities across that state," says Stellato.

The researchers say that this approach, guided by epidemiological and socioeconomic factors, could help inform strategic decision-making. Compared to alternative approaches based solely on population and social vulnerability, this approach leads to a greater reduction in overdose deaths and the number of people with OUD.

According to the Centers for Disease Control and Prevention (CDC), around 500,000 people have died from overdoses involving both illicit and prescription opioids from 1999 to 2019. Currently, the main treatment for OUD is medication-assisted treatment (MAT), which has been proven to sustain patient recovery and prevent future overdoses.

Although access to these treatment medications has expanded in the last decade, there are still major gaps in access across the United States, especially in rural areas with underdeveloped health infrastructures.

"The epidemic evolves differently in different states, and policies related to opioid treatment should be reflective of the needs of each state. It is critical to have tailored policies; this is not a one-size-fits-all issue. By optimizing treatment facility locations and budget allocations at the state level, there is potential to significantly improve health outcomes," concludes Luo.

Link to full study.

About INFORMS and Manufacturing & Service Operations Management

INFORMS is the leading international association for data and decision science professionals. Manufacturing & Service Operations Management, one of 17 journals published by INFORMS, is a premier academic journal that covers the production and operations management of goods and services including technology management, productivity and quality management, product development, cross-functional coordination and practice-based research. More information is available at www.informs.org or @informs.

/Public Release. This material from the originating organization/author(s) might be of the point-in-time nature, and edited for clarity, style and length. Mirage.News does not take institutional positions or sides, and all views, positions, and conclusions expressed herein are solely those of the author(s).View in full here.