Chatbot for Opioid Addiction

Overseen By Delta-Marie Lewis, BA

Age: 18+

Sex: Any

Trial Phase: Phase 1 & 2

Sponsor: Dimagi Inc.

Must be taking: Opioid treatment

Disqualifiers: Cognitive impairments, Unstable medical condition

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 12 weeks

55 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to determine if an AI chatbot can assist individuals recovering from opioid addiction. Researchers seek to evaluate whether the chatbot can reduce drug use, improve appointment attendance, and enhance users' sense of control over their recovery. Participants will engage with the chatbot for 12 weeks to prepare for appointments, access resources, and learn recovery techniques. This trial suits those receiving medication for opioid use disorder, who have reliable internet access, and are comfortable using a mobile device. As a Phase 1, Phase 2 trial, the study focuses on understanding the chatbot's functionality in individuals and measuring its effectiveness in a smaller group, offering participants an opportunity to contribute to innovative recovery solutions.

Do I need to stop my current medications to join the trial?

The trial does not specify if you need to stop your current medications. It seems you can continue your medication treatment for opioid use disorder while participating.

What prior data suggests that this chatbot is safe for patients in opioid use recovery?

Research has shown that AI chatbots designed to aid opioid addiction recovery have been promising in past studies. For instance, one study found that using AI to screen for opioid use disorder reduced the likelihood of patients returning to the hospital within 30 days by 47%. This indicates that AI tools, such as chatbots, can effectively manage care for opioid use disorder.

AI technology has also facilitated screening and referrals for treatment of substance use disorders. While this does not directly address the safety of using a chatbot, it demonstrates positive outcomes for AI tools in healthcare.

Regarding safety, AI chatbots are considered low-risk because they are software-based and do not involve medication or physical treatments. However, since this trial is in its early stages, specific data on the chatbot being tested is limited. Overall, evidence on AI in healthcare suggests it is a well-tolerated approach with potential benefits for supporting recovery from opioid use disorder. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about using a chatbot for opioid addiction because it offers a new way to support recovery through technology. Unlike traditional treatments like medication-assisted therapy or counseling sessions, this chatbot provides 24/7 support and can be accessed from a mobile device, making it convenient and always available. It aims to enhance follow-up care by offering personalized interactions and reminders that can aid in staying on track with recovery goals. By leveraging digital tools, this approach could potentially reach more people and offer continuous support, which is a game-changer in addiction recovery.

What evidence suggests that this chatbot is effective for opioid addiction recovery?

Research has shown that AI tools can help manage opioid use disorder. One study found that patients using AI screening were 47% less likely to be readmitted to the hospital within 30 days after discharge. Another study suggested that app-based support, such as programs rewarding positive behavior, improves treatment outcomes when combined with medication for opioid use disorder (MOUD). These findings indicate that digital tools, including chatbots, can aid recovery by reducing hospital readmission rates and enhancing treatment success. In this trial, participants will have access to a chatbot for 12 weeks to support follow-up care and recovery needs. Although specific data on chatbots is limited, early evidence suggests they might assist in substance use recovery by providing easy-to-access support and resources. ^{6 7 8 9 10}

Who Is on the Research Team?

Jonathan Jackson, MEng

Principal Investigator

Dimagi Inc.

Y. Xian Ho, PhD

Principal Investigator

Dimagi Inc.

Are You a Good Fit for This Trial?

This trial is for individuals in recovery from opioid addiction who are currently on medication-assisted treatment. Participants should be willing to use an AI chatbot for support over a 12-week period and provide feedback through surveys.

Inclusion Criteria

I can take part in a remote interview.

Own or have reliable access to Wi-Fi or a cellular network

I am currently receiving treatment for opioid use disorder at MGH.

Exclusion Criteria

Has any cognitive, visual, or auditory impairments that may prevent the participant from using the chatbot on a mobile device

Unstable medical condition that compromises the ability to safely participate

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive access to a chatbot for 12 weeks to support follow-up care and recovery needs

12 weeks

Virtual interaction with the chatbot

Follow-up

Participants are monitored for changes in substance use disorder severity, psychological health, self-efficacy, and user satisfaction

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• Chatbot

Trial Overview The study tests whether an AI chatbot can help patients with opioid use disorder by reducing drug use, improving appointment adherence, empowering self-management of recovery, and easing the workload of primary care teams.

How Is the Trial Designed?

Group I: Chatbot Experimental Treatment 1 Intervention

Participants will receive access to a chatbot for 12 weeks that can be used from a mobile device to support follow-up care and recovery needs.

Who Is Running the Clinical Trial?

Dimagi Inc.

Lead Sponsor

Trials

10

Recruited

9,300+

University of California, Los Angeles

Collaborator

Trials

1,594

Recruited

10,430,000+

National Institute on Drug Abuse (NIDA)

Collaborator

Trials

2,658

Recruited

3,409,000+

Massachusetts General Hospital

Collaborator

Trials

3,066

Recruited

13,430,000+

Citations

1. nih.gov nih.gov/news-events/news-releases/ai-screening-opioid-use-disorder-associated-fewer-hospital-readmissions

AI screening for opioid use disorder associated with fewer ... Patients with AI screening had 47% lower odds of being readmitted to the hospital within 30 days after their initial discharge.

2. jamanetwork.com jamanetwork.com/journals/jamanetworkopen/fullarticle/2827185

Smartphone App–Based Contingency Management and ... These findings suggest that adding app-based contingency management to MOUD is associated with better treatment outcomes in clinical settings.

3. nature.com nature.com/articles/s44184-024-00086-7

Evaluating a mobile app's effects on depression and ... This study evaluated the feasibility, acceptability, and preliminary effectiveness of a mobile application designed to address these symptoms in individuals ...

4. clinicaltrials.gov clinicaltrials.gov/study/NCT06845878?term=AREA%5BSponsorSearch%5D(COVERAGE%5BFullMatch%5DEXPANSION%5BNone%5D(%22Dimagi%20Inc.%22))&rank=1

A Chatbot to Support Substance Use Recovery Researchers will investigate the effects of using a chatbot to support follow-up care for patients in opioid use recovery. Participants will: Receive access to ...

5. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC7861202/

Outcomes for patients receiving telemedicine-delivered ... Additionally, rates of new Hepatitis C infections and newborns with Neonatal Opioid Withdrawal Syndrome have risen more rapidly in rural areas [22, 23].

6. recoveryanswers.org recoveryanswers.org/research-post/artificial-intelligence-smartphones-predicting-opioid-use-outcomes/

Artificial intelligence and smartphones for predicting opioid ... Primary outcomes included: 1) self-reported non-prescribed opioid use (via daily smartphone surveys), 2) self-reported buprenorphine nonadherence (via daily ...

7. nida.nih.gov nida.nih.gov/news-events/news-releases/2025/04/ai-screening-for-opioid-use-disorder-associated-with-fewer-hospital-readmissions

AI screening for opioid use disorder associated with fewer ... Patients with AI screening had 47% lower odds of being readmitted to the hospital within 30 days after their initial discharge.

8. mdpi.com mdpi.com/2673-2688/6/6/113

A Pilot Study of an AI Chatbot for the Screening ... AI technology may allow for improved access to SUD screening and treatment referrals, a critical step in responding to the opioid crisis. Keywords: artificially ...

9. bmjopen.bmj.com bmjopen.bmj.com/content/15/11/e102796

Increasing timely access to evidence-based treatment for ... This pilot study will test the feasibility of RecoveryPad to link eligible participants to initiate MOUD while collecting data to inform ongoing system dynamics ...

10. health.ny.gov health.ny.gov/health_care/medicaid/ebbrac/2025/docs/2025-07_hlth_tech_assessment.pdf

Treatment of Opioid Use Disorder Delivered Exclusively by ... These studies found treatment of OUD exclusively by telehealth was not significantly different for retention in treatment outcomes or rates of.