Opioid Use Disorder
Conditions
Keywords
opioid use disorder
Brief summary
This study aims to develop and evaluate dynamic treatment regimes (DTRs) to improve personalized care for individuals with opioid use disorder (OUD). Using machine learning methods and longitudinal data from a national behavioral health provider, the investigators will identify optimal treatment sequences that minimize the risk of overdose and improve recovery outcomes. A pilot hybrid factorial SMART trial will be conducted to assess the feasibility and acceptability of implementing these personalized treatment decision rules in real-world clinical settings.
Detailed description
This project supports the development and testing of dynamic treatment regimes (DTRs) for individuals with opioid use disorder (OUD), leveraging clinical and behavioral data from Discovery Behavioral Health and linked administrative records. In the first phase, multiple machine learning approaches (e.g., Q-learning, causal forests) will be used to estimate and validate DTRs that recommend tailored sequences of care based on patient characteristics and treatment response. The DTRs will be evaluated based on their ability to reduce fatal and non-fatal opioid overdose risk and hospital-based service use. In the second phase, the investigators will conduct a pilot hybrid factorial Sequential Multiple Assignment Randomized Trial (SMART) to test the feasibility and acceptability of implementing the highest-performing DTR in a clinical setting. This pilot study will assess recruitment and retention, adherence to assigned treatment paths, and the practicality of integrating the DTR into routine care. The findings will inform a future full-scale trial aimed at improving personalized care for OUD and outcomes.
Interventions
A medication treatment component delivered in Week 1 as part of a 2×2 factorial SMART design. The exact content (e.g., treatment modality or intensity) will be finalized based on model results from Aim 1, which identifies optimal dynamic treatment regimes.
BEHAVIORALpsychotherapy
A behavioral treatment component delivered in Week 1 as part of a 2×2 factorial SMART design. The exact content (e.g., treatment modality or intensity) will be finalized based on model results from Aim 1, which identifies optimal dynamic treatment regimes.
Sponsors
National Institute on Drug Abuse (NIDA)
Brigham and Women's Hospital
Study design
Allocation
RANDOMIZED
Intervention model
SEQUENTIAL
Primary purpose
TREATMENT
Masking
NONE
Masking description
This is an open-label trial; no participants, providers, or investigators are masked to treatment assignment.
Intervention model description
The study uses a Sequential Multiple Assignment Randomized Trial (SMART) design. Participants are initially randomized in a 2x2 factorial structure in Week 1 to receive one of four treatment combinations. In Weeks 2-4, additional weekly treatment components are assigned based on participant response and predefined decision rules. This structure allows for evaluation of dynamic treatment regimens tailored to individual needs and evolving treatment response.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age 18 or older * Diagnosed with opioid use disorder (OUD) * Receiving care at a participating Discovery Behavioral Health site * Able to provide informed consent
Exclusion criteria
* Significant cognitive impairment or psychiatric instability that would prevent participation * Current incarceration or involuntary commitment
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| CAT-SUD severity scores | 4 weeks | Weekly Computerized Adaptive Test for Substance Use Disorder severity T-score. Scores range 0-100 (≈5-point precision). Higher scores indicate a greater SUD symptom burden/risk, while lower scores indicate fewer symptoms/lower risk. Prior validation studies have used \<50 = low, 50-70 = intermediate, \>70 = high severity/risk thresholds. Computerized Adaptive Test for Substance Use Disorder provides a dimensional severity score (not a diagnosis). Change is assessed week-to-week. |
| Retention in treatment | 4 weeks | Whether participants remained engaged in behavioral health treatment through the end of the 4-week study period. |
| Patient and clinician satisfaction | 4 weeks | Participant- and provider-reported satisfaction with the trial experience and procedures, assessed via standardized surveys. |
| Clinical fidelity to intervention protoco | Weekly over 4-week study period | Fidelity of intervention delivery assessed via clinician checklists or independent fidelity ratings, evaluating adherence to protocol for each assigned treatment component. |
| Data completeness and consistency | Throughout the 4-week trial | Proportion of participants for whom ethical standards are fully maintained (e.g., informed consent obtained, no reported violations). Proportion of participants for whom ethical standards are fully maintained (e.g., informed consent obtained, no reported violations). Proportion of EHR and survey data points with missing or inconsistent entries. Thresholds for success include \<5% missingness or inconsistency. |
| Timeliness of EHR data entry | Weekly throughout the 4-week trial | Proportion of EHR entries recorded within 48 hours of patient interaction. |
Countries
United States
Contacts
Primary ContactJason B Gibbons, PhD
Outcome results
None listed