Wrist wearable to detect opioid dosing and measure withdrawal

A Study to Train a Machine Learning Algorithm for an Evaluation of the Use of Biometric Data Captured at the Wrist for the Identification of Acute Opioid Use Events and the Quantification of Opioid Withdrawal in Opioid Dependent Individuals

This study will test whether a wrist-worn biometric band can detect when people with opioid use disorder take their medication and measure their withdrawal levels during medication induction.

Quick facts

• Phase: Not applicable
• Study type: Interventional
• Enrollment: 420 (estimated)
• Ages: 22 Years and up
• Sex: All
• Sponsor: OpiAID (Industry-sponsored)
• Locations: 4 sites (Wilmington, North Carolina and 3 other locations)
• Trial ID: NCT07405398 on ClinicalTrials.gov

What this trial studies

This multi-center, outpatient study will collect time-stamped biometric data from a wrist-worn device (the OpiAID Strength Band Platform™) in people starting medication for opioid use disorder with methadone or buprenorphine. Investigators will train a machine learning algorithm on patient-specific physiological signals to identify acute medication dosing events and to quantify withdrawal. The primary technical goal is to achieve at least 80% classification performance on a receiver operating characteristic curve for dosing event detection. Withdrawal quantification will be compared to time since last dose and to the SOWS in a non-inferiority analysis.

Who should consider this trial

Good fit: Adults aged 22 or older with DSM-5 opioid use disorder who are eligible for induction onto methadone or buprenorphine and who can independently operate a smartwatch and communicate in English are ideal candidates.

Not a fit: People who cannot use a wrist device (for example due to wrist tattoos or inability to operate smartwatch apps), those not undergoing MOUD induction, non-English speakers, or those with severe comorbid conditions or diminished decision-making capacity are unlikely to benefit from participation.

Why it matters

Potential benefit: If successful, the platform could provide objective, continuous detection of dosing events and real-time withdrawal measurement to help clinicians tailor treatment and intervene earlier.

How similar studies have performed: Previous small studies using wearables and machine learning have shown promise for detecting substance use signals and withdrawal, but applying this approach specifically to MOUD induction with the OpiAID platform is relatively novel and not yet proven.

Eligibility criteria

Inclusion Criteria:

* Male or female
* Age ≥22 years at signing of informed consent
* Patients with a DSM-5 diagnosis of OUD who are eligible for MOUD induction with methadone or buprenorphine

Exclusion Criteria:

* Sleeve tattoo covering the wrist
* Subject unable to independently navigate and operate smartwatch applications
* Subject not proficient with written and spoken English
* Subject determined likely to be non-compliant by physician/HCP
* Subject likely to not be available to complete all protocol-required study visits or procedures, and/or to comply with all required study procedures to the best of the subject and investigator's knowledge.
* History or evidence of any other clinically significant disorder, condition, or disease that, in the opinion of the investigator, would pose a risk to subject safety or interfere with the study evaluation, procedures or completion.
* Subject has diminished decision making capability

Where this trial is running

Wilmington, North Carolina and 3 other locations

• Coastal Horizon — Wilmington, North Carolina, United States (Recruiting)
• Community Medical Services — Austin, Texas, United States (Recruiting)
• Community Medical Services — Austin, Texas, United States (Recruiting)
• Community Medical Services — Cedar Park, Texas, United States (Recruiting)

Study contacts

• Study coordinator: Trace Brookins

Conditions Treatment for Opioid Use Disorder