Adaptive Mobile Interventions to Reduce Cancer Risk Behaviors
Purpose
Tobacco use remains the leading cause of preventable death, causing over 400,000 annual deaths in the United States alone. Smartphone-based interventions, particularly those leveraging real-time adaptive messaging, represent a promising yet underutilized approach to delivering personalized tobacco and cannabis treatment. The investigator's ongoing NCI funded micro-randomized trial (MRT; R01 CA246590) has shown initial feasibility in reducing smoking urges through situationally tailored cognitive-behavioral therapy (CBT) and mindfulness-based acceptance and commitment-based therapy (ACT) messages triggered by real-time contextual data (e.g., geolocation, momentary stress). To advance from a static MRT framework to a dynamic, data-driven just-in-time adaptive intervention (JITAI), this project aims to develop, test, and refine a reinforcement learning (RL) algorithm that can continuously adapt to user needs in real-time, enhancing treatment outcomes for various tobacco and cannabis products. To ensure optimal usability and engagement, the investigators will conduct user-centered testing with the developed RL-based intervention delivery in one cohort (N=7) over 45 days. This will include usability assessment via the System Usability Scale, analysis of app interaction metrics, and semi-structured interviews to gather feedback for refining message content, timing, and design.
Condition
- Smoking Cessation
Eligibility
- Eligible Ages
- Between 18 Years and 40 Years
- Eligible Sex
- All
- Accepts Healthy Volunteers
- Yes
Inclusion Criteria
- live in the U.S.; - are between 18 and 40 years of age; - own a smartphone with iOS and Android operating system and GPS capabilities; - are carrying smartphone every day; - are willing to participate in the study for 44 days and give the research team access to the phone GPS data; - have smoked ≥100 cigarettes in the participant's life and currently smoke at least 3 cigarettes per day on 5 or more days of the week; - are planning to quit smoking within the next 30 days.
Exclusion Criteria
- None
Study Design
- Phase
- N/A
- Study Type
- Interventional
- Allocation
- N/A
- Intervention Model
- Single Group Assignment
- Primary Purpose
- Treatment
- Masking
- None (Open Label)
Arm Groups
| Arm | Description | Assigned Intervention |
|---|---|---|
|
Experimental RL-informed intervention |
Participants complete a 14-day Ecological Momentary Assessment (EMA) training phase using a smartphone app (MetricWire), during which the participant responds to up to 3 randomly prompted and cigarette-triggered EMA surveys per day while the app passively collects GPS data. These data are used to identify high-risk locations and time periods and to inform a previously trained reinforcement learning (RL) algorithm. During the subsequent 30-day intervention phase, the RL algorithm delivers personalized intervention messages (cognitive-behavioral therapy [CBT], acceptance and commitment therapy [ACT], or attention control) triggered by geofence entry at high-risk locations. |
|
Recruiting Locations
Baltimore, Maryland 21205
More Details
- Status
- Recruiting
- Sponsor
- Johns Hopkins Bloomberg School of Public Health