Machine Learning + Peer Support for Substance Use Disorder

Overseen by James J Mahoney, Ph.D.

Age: 18+

Sex: Any

Travel: May Be Covered

Time Reimbursement: Varies

Trial Phase: Academic

Waitlist Available

Sponsor: West Virginia University

Disqualifiers: Inability to give consent, others

No Placebo Group

Trial Summary

What is the purpose of this trial?

The goal of this clinical trial is to study the relationship between substance cravings, cognitive performance, behaviors, and physiological markers in individuals with substance use disorder, as well as the effects of peer recovery intervention in response to abnormal biomarker data detected by wearable technology (e.g., Oura ring, smart watch) and participant responses to questionnaires and cognitive tasks completed on the RNI Health application.

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

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your doctor.

What data supports the effectiveness of the treatment PRSS, Peer Recovery Support, PRSS Intervention for Substance Use Disorder?

Research suggests that peer recovery support services (PRSS) can help reduce substance use and relapse rates, improve relationships with treatment providers, and increase treatment satisfaction for individuals with substance use disorder. However, more rigorous studies are needed to confirm these benefits and understand how best to implement PRSS. ^{1 2 3 4 5}

Is the Machine Learning + Peer Support for Substance Use Disorder treatment safe for humans?

Research on Peer Recovery Support Services (PRSS) shows that using peer interventionists in substance use disorder treatment is generally safe, with no reported negative effects on those delivering the intervention. ^{4 5 6 7 8}

How does the Machine Learning + Peer Support treatment for Substance Use Disorder differ from other treatments?

This treatment is unique because it combines machine learning algorithms, which predict stress and drug cravings using data like GPS, with peer support, where individuals with similar experiences provide nonprofessional assistance. This approach aims to deliver timely interventions and support, unlike traditional treatments that may not use real-time data or peer involvement. ^{3 5 9 10 11}

Research Team

James J Mahoney, Ph.D.

Principal Investigator

West Virginia University Rockefeller Neuroscience Institute

Eligibility Criteria

This trial is for adults over 18 with substance use disorders who are currently or were previously treated at a WVU Medicine Clinic, or residents of sober living facilities. Participants must be able to consent and download the required health app and wearable device apps on their smart devices.

Inclusion Criteria

I am 18 years old or older.

Current or previous enrollment as a patient in a WVU Medicine Clinic for treatment of substance use disorder (e.g., residential, detoxification, inpatient, or outpatient), or a resident of a sober living facility.

Exclusion Criteria

I am unable to understand and give consent for treatment.

Inability to download the RNI Health app and wearable device apps onto their smart device

Trial Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Initial Monitoring

Participants are monitored for 3 months to collect baseline data using wearable technology and the RNI Health app

12 weeks

Continuous monitoring

Randomization and Intervention

Participants are randomized to either standard-of-care treatment or PRSS intervention, with continuous monitoring and periodic assessments

Up to 5 years

Continuous monitoring, periodic assessments

Follow-up

Participants are monitored for safety and effectiveness after intervention

4 weeks

Treatment Details

Interventions

• PRSS (Behavioural Intervention)

Trial Overview The study aims to predict relapse in individuals with substance use disorder using machine learning technology that analyzes data from wearables like Oura rings, smartwatches, and responses on the RNI Health app. It also tests if peer recovery interventions can prevent relapse when prompted by abnormal biomarkers.

Participant Groups

Group I: PRSS intervention Experimental Treatment 1 Intervention

Participants receiving PRSS intervention will be contacted by the PRSS who will be blinded (not knowing whether an alert was caused by data anomaly or a random generation), and will contact the participant by phone and assess the need for assistance. PRSS will follow-up with the participant to assist participant if needed (once after the initial alert and then a second follow-up).

Group II: Treatment as usual Active Control 1 Intervention

Participants will receive standard of care treatment as usual and will receive no contact from a peer recover support specialist (PRSS intervention) when data anomalies are detected by machine learning algorithms.

Who Is Running the Clinical Trial?

West Virginia University

Lead Sponsor

Trials

192

Recruited

64,700+

Dr. William P. Petros

West Virginia University

Chief Medical Officer

PharmD from West Virginia University

Dr. Clay B. Marsh

West Virginia University

Chief Executive Officer since 2015

MD from West Virginia University, Bachelor’s in Biology from West Virginia University

Findings from Research

A new 13-item peer support scale was assessed using Rasch analysis in a study involving 408 adults who had completed inpatient treatment for substance-use disorder, confirming that most items measure the same underlying concept of peer support.

This standardized scale can be a valuable tool for both researchers and treatment providers to measure peer support, which is known to help prevent relapse in individuals recovering from substance abuse.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Peer Support Scale for Adults Treated for Psychoactive Substance-Use Disorder: A Rasch Analysis. Mazurek, KD., Ciesla, JR.[2020]

Clients in outpatient substance use disorder treatment who attended self-help groups and set treatment goals were more likely to remain in treatment for over 90 days and successfully complete it, based on a study using machine learning on data from 2018 to 2021.

Additional factors that contributed to successful treatment outcomes included being linked to a primary care provider and receiving supplemental nutrition assistance, highlighting the importance of social support in recovery.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Determinants of outpatient substance use disorder treatment length-of-stay and completion: the case of a treatment program in the southeast U.S. Baird, A., Cheng, Y., Xia, Y.[2023]

Peer support groups have shown potential benefits in addiction treatment, including reductions in substance use, increased treatment engagement, and improved self-efficacy among participants, based on a review of ten studies conducted in the U.S. since 1999.

Despite these promising findings, the overall lack of rigorously tested empirical studies limits the ability to draw definitive conclusions about the effectiveness of peer support as a formal intervention in addiction treatment.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Benefits of peer support groups in the treatment of addiction. Tracy, K., Wallace, SP.[2020]

In a pilot study involving 80 adults with recent non-fatal opioid overdoses, trained peer interventionists successfully delivered a Peer Recovery Support Services (PRSS) intervention, achieving a treatment enrollment success rate between 16% and 60%.

The interventionists reported no negative effects from their role, indicating that peer-led interventions can be implemented safely and effectively with limited training, although further research is needed to understand the factors influencing their varying success rates.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The feasibility and safety of training patients in opioid treatment to serve as peer recovery support service interventionists. Kropp, F., Wilder, C., Theobald, J., et al.[2022]

The Peer Recovery Program implemented in 20 hospitals provided 24/7 support for patients with substance use disorder, receiving referrals during over 30,000 patient visits from 2016 to 2019, with a high acceptance rate of continued support services between 74.8% and 83.0%.

The program demonstrated efficient response times, with Recovery Specialists arriving at the patient's bedside within an average of eight minutes, and facilitated numerous follow-up contacts, although further evidence of improved patient outcomes is necessary for broader implementation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Implementing hospital-based peer recovery support services for substance use disorder. Liebling, EJ., Perez, JJS., Litterer, MM., et al.[2021]

Active users of the Sober Grid app, a digital recovery support service, showed an average sobriety length of 195.5 days, indicating that engagement with the platform may positively influence recovery outcomes.

Demographic factors like age and gender, along with user activity such as the number of check-ins, were found to be significant predictors of sobriety length and relapse, suggesting that tailored interventions could be developed based on these insights.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Digital recovery networks: Characterizing user participation, engagement, and outcomes of a novel recovery social network smartphone application. Ashford, RD., Giorgi, S., Mann, B., et al.[2021]

Peer recovery support services (PRSS) have been integrated into the recovery process for opioid use disorder (OUD), but their effectiveness on clinical outcomes remains unclear, as only 12 out of 123 studies met the inclusion criteria for review.

Most studies reported on PRSS engagement and medication for OUD (MOUD) initiation, but findings were inconsistent and varied due to the lack of standardized PRSS interventions and methodological limitations, indicating a need for further research before widespread implementation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Effectiveness of peer recovery support services on stages of the opioid use disorder treatment cascade: A systematic review. Gormley, MA., Pericot-Valverde, I., Diaz, L., et al.[2022]

Mobile sensing technology has the potential to improve data collection and predictive capabilities regarding substance use and relapse, but current research is limited, with only six studies focusing on alcohol use identified in this review.

Most studies primarily focused on identifying ongoing substance use rather than predicting future use, highlighting a need for more research on diverse substances and clinical populations to enhance understanding and intervention strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Mobile Sensing in Substance Use Research: A Scoping Review. Lauvsnes, ADF., Langaas, M., Toussaint, P., et al.[2021]

A study involving 189 outpatients with opioid-use disorder used a randomForest algorithm to predict cravings for heroin and cocaine, achieving high overall accuracy (up to 0.93) in predicting when cravings would not occur, but lower accuracy in predicting actual cravings.

The findings suggest that while passive monitoring through GPS data can provide some predictive insights, accurately predicting subtle events like cravings or stress may require active user input, as high overall accuracy can sometimes hide the prevalence of false alarms.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. Epstein, DH., Tyburski, M., Kowalczyk, WJ., et al.[2023]

References

1. United States pubmed.ncbi.nlm.nih.gov

A Peer Support Scale for Adults Treated for Psychoactive Substance-Use Disorder: A Rasch Analysis. [2020]

2. England pubmed.ncbi.nlm.nih.gov

Determinants of outpatient substance use disorder treatment length-of-stay and completion: the case of a treatment program in the southeast U.S. [2023]

3. New Zealand pubmed.ncbi.nlm.nih.gov

Benefits of peer support groups in the treatment of addiction. [2020]

4. United States pubmed.ncbi.nlm.nih.gov

The feasibility and safety of training patients in opioid treatment to serve as peer recovery support service interventionists. [2022]

5. Switzerland pubmed.ncbi.nlm.nih.gov

Lived Experience in New Models of Care for Substance Use Disorder: A Systematic Review of Peer Recovery Support Services and Recovery Coaching. [2023]

6. England pubmed.ncbi.nlm.nih.gov

Implementing hospital-based peer recovery support services for substance use disorder. [2021]

7. United States pubmed.ncbi.nlm.nih.gov

Digital recovery networks: Characterizing user participation, engagement, and outcomes of a novel recovery social network smartphone application. [2021]

8. Ireland pubmed.ncbi.nlm.nih.gov

Effectiveness of peer recovery support services on stages of the opioid use disorder treatment cascade: A systematic review. [2022]

9. United States pubmed.ncbi.nlm.nih.gov

Mobile Sensing in Substance Use Research: A Scoping Review. [2021]

10. England pubmed.ncbi.nlm.nih.gov

Prediction of stress and drug craving ninety minutes in the future with passively collected GPS data. [2023]

11. England pubmed.ncbi.nlm.nih.gov

A Bayesian mixed effects support vector machine for learning and predicting daily substance use disorder patterns. [2022]