New app in development aims to stop opioid relapses before they happen
Researchers at the University of Wisconsin—Madison have received a $3.42 million grant from the National Institutes of Health (NIH) to develop a mobile phone-based app to prevent opioid relapse among those trying to recover.
The project builds on the prior work that Dhavan Shah, Louis A. & Mary E. Maier-Bascom Professor in UW-Madison’s School of Journalism and Mass Communication, and John Curtin, Professor and Director of Clinical Training in Department of Psychology, have done detecting and predicting relapse.
The broad goals of this project are to develop and deliver models to forecast the day-by-day probability of opioid and other drug use among people trying to abstain from drugs while in recovery. This lapse risk prediction model will be generated using the Addiction-Comprehensive Health Enhancement Support System (A-CHESS) mobile app, a tool developed by researchers in the UW’s Center for Health Enhancement System Studies.
The study will focus on about 500 participants who are abstaining from drug use while in recovery. The study will follow 12 months of their recovery, with observations occurring as early as one week post-abstinence and as late as 18 months post-abstinence across participants in the sample.
“Relapse can happen early in recovery for alcohol and substance use disorders, but it can also happen months, and even years, after someone quits,” Curtin says. “One of the biggest challenges that people with alcohol and substance use disorders have is to continually monitor their recovery and look out for risks for relapse, essentially for the rest of their lives.”
While relapse often seems to come out of the blue from the perspective of the participant, Shah says, hindsight often yields indicators that the individual was a risk. The clues can come from what they post, who they talk with, and the places they frequent.
“Over the past five years, we have been working to use emerging mobile sensing capabilities from smartphones and wearable sensors to build models that can predict, in real time, the likelihood that someone will lapse back to drug use,” Shah says. Working with his students, he recently published two articles predicting the risk of relapse based solely on the language that participants used while engaging with the A-CHESS system.
Curtin’s lab is about to complete another NIH funded project that has followed people with alcohol use disorder for the first 3 months of their sobriety and can already predict with better than 80 percent accuracy whether they will use alcohol on any given day. Using cell phone communications, including voice calls and texts, and GPS data to establish locations where individuals have used alcohol in the past, the researchers can monitor signals about the integrity of an individual’s recovery and abstinence.
“More importantly, we can do this passively using primarily information that is gathered automatically by their mobile phone use with almost no burden placed on the individual,” Curtin says.
This relapse risk signal can then be provided to the person to guide them to seek further support from friends, treatment providers or an mHealth app like A-CHESS that can provide “just-in-time” interventions in moments of high risk.
The current project extends Shah and Curtin’s work from alcohol use disorder to opioid use disorder. It will also focus on recruiting a nationally representative sample, including participants pursuing recovery with Wisconsin’s Aurora Health Care, which has signed on as a partner.
“This will be important because the signals that predict relapse back to opioid use are likely different for someone who lives in an urban versus suburban versus rural part of the country,” Shah says.
For more information on the project, contact John Curtin at email@example.com.