Previously submitted to: Journal of Participatory Medicine (no longer under consideration since Apr 15, 2025)
Date Submitted: Nov 22, 2024
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Be Well Buddy: A feasibility study to explore the use of an AI Chatbot to facilitate access to screening and treatment for substance use disorders
ABSTRACT
Background:
Despite recent declines in opioid deaths in the U.S., there remains an urgent need to facilitate access to resources to help people prevent, screen and treat substance use disorders (SUD). The ubiquity of cell phones and text messaging in the US has facilitated effective interventions for SUD. Emerging technologies using artificial intelligence (AI) to make texting more dynamic and tailored have potential but remain untested. We developed an interactive AI chatbot to raise awareness about SUD and to prompt users to screen and receive referrals for anxiety depression and SUD treatment and pilot tested the system to establish feasibility and usability for using the system with a network of SUD treatment clinics in Texas.
Objective:
Our objectives were to assess the usability, feasibility and acceptability of using an AI chatbot to convey information about substance use and to use the system to screen for substance use disorder, anxiety and depression.
Methods:
Using the People at the Center for Mobile Application Design (PACMAD) framework to assess usability, we enrolled a convenience sample of people either affiliated with one of the SUD treatment sites or invited by those affiliated to participate. Participants agreed to receive and engage with the AI chatbot via phone-based text messages. We sent push notifications via text several times each day for seven days to engage users in exchanges about SUD and to encourage them to screen for anxiety, depression and SUD. We invited a subset of 13 participants to complete an in-depth interview describing their experience. We documented user satisfaction, perceived appropriateness of messages and system, logged all incoming and outgoing messages, documented any system errors, and documented screenings completed by users.
Results:
There were 91 participants enrolled between July and September 2024 and 80% of participants (n=73) initiated at least one communication with the system; of these, 39% completed at least one screener, and 83% of those screening were referred for care. Participants expressed satisfaction with the system and perceived it to be appropriate.
Conclusions:
It is possible to engage users to interact with an AI chatbot focused on SUD. This may offer an opportunity to scale and automate dissemination of critical information on SUD and resources for self-screening that will not reinforce stigma. Clinical Trial: Not applicable, this was not a clinical trial.
Citation
The author of this paper has made a PDF available, but requires the user to login, or create an account.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.