U.S. flag An official website of the United States government

On Oct. 1, 2024, the FDA began implementing a reorganization impacting many parts of the agency. We are in the process of updating FDA.gov content to reflect these changes.

U.S. Food and Drug Administration
  1. Home
  2. Science & Research
  3. Science and Research Special Topics
  4. Advancing Regulatory Science
  5. Developing a risk prediction engine for relapse in opioid use disorder
  1. Advancing Regulatory Science

Developing a risk prediction engine for relapse in opioid use disorder

CERSI Collaborators: Jessilyn Dunn, PhD; Jennifer Goldsack, MChem, MA, MBA, OLY; Lauren Lederer; Candice Taguibao, MPH; Danielle Stefko; Samantha McClenahan, PhD

FDA Collaborators: Anindita Saha; Leeda Rashid, MD; Jisun Yi, MD; Roxane Modares, MPH, Gioia Guerrieri, DO; Robert Wright, PhD

Project Start Date: September 8, 2023

Regulatory Science Challenge

In the United States, 2.7 million people ages 12 or older reported suffering from opioid use disorder (OUD) in 2020, with relapse rates of 65-70%. In addition, 75% of overdose deaths in the U.S. are due to opioids and the cost of the epidemic is estimated at $1.5 trillion.

This Triangle CERSI project, which includes a collaboration between Duke University, University of North Carolina, and the Digital Medicine Society (DiMe), will build a protocol for a tool that uses data from digital sensor technologies, like wearables, to predict when people affected by OUD might relapse. Investigators aim to generate a scientific plan to use consumer technologies and the data they collect to predict relapse and to inform early-intervention strategies to provide every person affected by OUD with the care they need, when they need it most.

Project Description and Goals

This project will:

  1. Assess/select the phenotype(s), or observable physical properties, of persons/patients with OUD on which to base the study protocol.
  2. Study the behaviors/physiologic responses connected to opioid use relapse that can be detected with digital sensor technology.
  3. Explore appropriate technologies that can be used to collect this data.
  4. Create a protocol for a study to develop and test an OUD risk prediction tool.

To complete this work, investigators will:

  • Review existing research to determine what is currently known about relapse in OUD (e.g., physiological, behavioral, social).
  • Seek perspectives from a diverse set of experts, people affected by OUD, and their health care providers.
  • Develop a scientific plan for an OUD risk prediction tool, informed by these findings.

Findings from this project will inform the development of an evidence-based, scientific plan to build an equitable, data-driven tool to predict relapse in a person living with OUD. This tool offers a low burden, high reach, and scalable solution for preventing lapses & relapses for all individuals with OUD, offering a pathway to improve care for all people affected by OUD.

 

Back to Top