Artificial intelligence interventions focused on opioid use disorders: A review of the gray literature

ABSTRACT

Background

With the artificial intelligence (AI) paradigm shift comes momentum toward the development and scale-up of novel AI interventions to aid in opioid use disorder (OUD) care, in the identification of overdose risk, and in the reversal of overdose.

Objective

As OUD-specific AI interventions are relatively recent, dynamic, and may not yet be captured in the peer-reviewed literature, we conducted a review of the gray literature to identify literature pertaining to OUD-specific AI interventions being developed, implemented and evaluated.

Methods

Gray literature databases, customized Google searches, and targeted websites were searched from January 2013 to October 2019. Search terms include: AI, machine learning, substance use disorder (SUD), and OUD. We also requested recommendations for relevant material from experts in this area.

Results

This review yielded a total of 70 unique citations and 29 unique interventions, which can be sub-divided into five categories: smartphone applications (n = 12); healthcare data-related interventions (n = 7); biosensor-related interventions (n = 5); digital and virtual-related interventions (n = 2); and ‘other’, i.e., those that cannot be classified in these categories (n = 3). While the majority have not undergone rigorous scientific evaluation via randomized controlled trials, several AI interventions showed promise in aiding the identification of escalating opioid use patterns, informing the treatment of OUD, and detecting opioid-induced respiratory depression.

Conclusion

This is the first gray literature synthesis to characterize the current ‘landscape’ of OUD-specific AI interventions. Future research should continue to assess the usability, utility, acceptability and efficacy of these interventions, in addition to the overall legal, ethical, and social implications of OUD-specific AI interventions.

KEYWORDS:

• Artificial intelligence
• interventions
• opioid use disorder

Disclosure of interest

The authors report no conflicts of interest.

Additional information

Funding

This work was undertaken through a Canadian Institutes of Health Research Planning and Dissemination Grant. SN is supported by a Michael Smith Foundation for Health Research’s (MSFHR) Health Professional Investigator Award and UBC’s Steven Diamond Professorship in Addiction Care Innovation. LT and RK are supported by a MSFHR Scholar Award. TB is supported by a University of British Columbia (UBC) Doctoral Fellowship.