Piloting a Reinforcement Learning Tool for Individually Tailoring Just-in-time Adaptive Interventions

Obesity Clinical Trial

Official title:

Piloting a Reinforcement Learning Tool for Individually Tailoring Just-in-time Adaptive Interventions

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT05751993
• Other study ID #: 22-0149
• Secondary ID: R21CA260092
• Status: Not yet recruiting
• Phase: N/A
• Start date: April 2024
• Est. completion date: December 2024

Study information

• Verified date: April 2024
• Source: UNC Lineberger Comprehensive Cancer Center
• Contact: Brooke Nezami, PhD, MA
• Phone: 919-966-5852
• Email: bnezami[@]unc.edu
• Is FDA regulated: No
• Study type: Interventional

Clinical Trial Summary

The purpose of this pilot study is to conduct a 12-week pilot feasibility study testing usability of the adapt learning tool (AdaptRL)in a weight loss intervention (ADAPT study). Building upon a previous just-in-time adaptive intervention (JITAI), a reinforcement learning tool will generate decision rules regarding which behavior change techniques, in which contexts, are most efficacious for promoting weight loss in a sample of 20 adults.

Description:

Reinforcement Learning (RL), a type of machine learning, holds promise for addressing the limitations of previous approaches to implementing JITAIs. Adaptive RL applications work by updating information about expected "rewards" (i.e., proximal outcomes) based on the results of sequentially randomized trials. In the context of mHealth, random delivery of intervention messages is referred to as a micro-randomized trial. To realize the potential of adaptive interventions to reduce health disparities in cancer prevention and control, mHealth interventionists first need a user-friendly RL tool that enables use of digital health participant data to continually adapt decision rules guiding highly tailored intervention delivery. This research team has developed a user-friendly, web-based application (AdaptRL) that reads in and analyzes user data (e.g., from Fitbit) in real-time, uses RL to efficiently conduct micro-randomized trials, and creates a JITAI tailored to optimize weight loss for each participant. The objective of this study is to test the feasibility of using the AdaptRL tool in a pilot weight loss study.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 20
• Est. completion date: December 2024
• Est. primary completion date: December 2024
• Accepts healthy volunteers: Accepts Healthy Volunteers
• Gender: All
• Age group: 18 Years to 55 Years

Eligibility

Inclusion Criteria:

1. Age 18-55 years

2. Body Mass Index of 25-40 kg/m2

3. Not adhering to the US physical activity guidelines of at least 150 moderate-to-vigorous intensity activity minutes/week

4. English-speaking and writing

5. No pre-existing medical condition(s) that preclude adherence to an unsupervised exercise program, diabetes treated with insulin, history of heart attack or stroke, current treatment for cancer, or inability to walk for exercise

6. Has a smartphone with a data and text messaging plan

Exclusion Criteria:

1. Current participation in another weight loss, physical activity, nutrition program, or research study

2. Currently taking weight loss medications

3. Currently pregnant or planning pregnancy in the next 3 months

4. Lost 10 or more pounds and kept it off in the last 6 months

5. History of weight loss surgery

6. Report a heart condition, chest pain during periods of activity or rest, loss of consciousness, joint or bone problems, medical conditions that could limit exercise, or prescription medicine used for blood pressure or heart condition on the Physical Activity Readiness Questionnaire (PAR-Q)

7. Type 1 diabetes or currently receiving medical treatment for Type 2 diabetes

8. Cancer treatment within the past 5 years

9. Tuberculosis

10. Health or psychological diagnoses that preclude participation in a prescribed dietary and exercise program, including diagnosis of schizophrenia or bipolar disorder, hospitalization for a psychiatric diagnosis in the past year, a diagnosis of alcohol or substance abuse

11. Report a past diagnosis of or receiving treatment for The Diagnostic and Statistical Manual of Mental Disorders, fourth edition, text revision (DSM-IV-TR) eating disorder (anorexia nervosa or bulimia nervosa).

12. Moving out of the area in the next 4 months

13. Out of town for a week or more during the study period

14. Another member of the household is a participant or staff member in this trial

15. Not willing to attend two study visits

16. Not willing to wear a Fitbit every day

Related Conditions & MeSH terms

• Obesity
• Overweight
• Overweight and Obesity

Intervention

Behavioral:
• ADAPT
The intervention is testing the feasibility of a reinforcement learning tool to pull in participants' behavioral data (calories, activity, and weight) and use this data along with participants' past behavioral goal achievements to deliver the type of message that should be most effective for a given participant at a given time. At each decision point (early morning, morning, midday, and evening on a daily basis), the system evaluates which intervention options a participant is eligible to receive, and randomly chooses one intervention option from that list. Then the participant is randomly assigned to either receive or not receive that intervention message (with a 50-50 probability).

Locations

Country	Name	City	State
United States	University of North Carolina at Chapel Hill	Chapel Hill	North Carolina

Sponsors (4)

Lead Sponsor	Collaborator
UNC Lineberger Comprehensive Cancer Center	Duke University, National Cancer Institute (NCI), RTI International

Country where clinical trial is conducted

United States, 

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Feasibility (success of using the AdaptRL Tool)	Feasibility as the success of using the AdaptRL Tool will be defined as the mean number of messages delivered per participant per day.	up to 12 weeks
Primary	Study engagement	Study engagement will be defined as the percent of person-days in which participants accessed the web app.	up to 12 weeks
Primary	Self-monitoring adherence	Self-monitoring adherence will be defined as the percent of person-days in which participants tracked at least one weight loss behavior (tracked calories, wore tracker, or self-weighed).	up to 12 weeks
Secondary	Message satisfaction	Message satisfaction will be defined as the percent of delivered messages that were rated as "liked" (compared to dislike or not rated).	up to 12 weeks
Secondary	Percent weight loss	Percent weight loss will be defined as weight change from baseline to 12 weeks calculated as a percent from baseline weight.	12 weeks
Secondary	Moderate-to-vigorous physical activity	Moderate-to-vigorous physical activity will be defined as the change in self-reported weekly minutes of moderate-to-vigorous physical activity as measured by the Paffenbarger Activity Questionnaire from baseline to 12 weeks. The minimum is 0, no maximum. Higher numbers represent higher minutes of weekly moderate-to-vigorous physical activity.	Baseline, 12 weeks
Secondary	Dietary intake	Dietary intake will be defined as the change in average daily calorie intake as measured by the Automated Self-Administered 24-hour (ASA 24-hour) dietary recalls from baseline to 12 weeks. Daily caloric intake is measured in kcals, with higher numbers indicating higher caloric intake.	Baseline, 12 weeks
Secondary	Adherence to calorie goal	Adherence to the calorie goal as the percent of person-days in which participants tracked their calories and stayed at or under their calorie goal will be measured by dietary self-monitoring data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Adherence to daily active minutes goal	Adherence to daily active minutes goal, the percent of person-days in which participants met their daily active minute goal, will be measured by activity tracker data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Adherence to daily self-weighing	Adherence to daily self-weighing, the percent of person-days in which participants self-weighed will be measured by Fitbit smart scales and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Adherence to daily self-weighing at the participant-day level	Adherence to daily self-weighing at the participant-day level, the percent of person-days weighed after the message randomization time until the end of the day will be measured by Fitbit smart scales and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Adherence to the daily self-weighing percent of person-days weighed	Adherence to the daily self-weighing percent of person-days weighed the day after the message randomization will be measured by Fitbit smart scales and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Achievement of active minutes goal	Achievement of active minutes goal, percent of person-days met active minutes goal after the message randomization time until the end of the day will be measured by activity tracker data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Achievement of active minutes goal percent of person-days	Achievement of active minutes goal percent of person-days met active minutes goal the day after the message randomization will be measured by activity tracker data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Achievement of calorie goal (at or under goal)	Achievement of calorie goal (at or under goal) percent of person-days met calorie goal after the message randomization time until the end of the day will be measured by dietary self-monitoring data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks
Secondary	Achievement of calorie goal (at or under goal) percent of person-days	Achievement of calorie goal (at or under goal) percent of person-days met calorie goal the day after the message randomization will be measured by dietary self-monitoring data tracked in the Fitbit app and transmitted via Application Programming Interface (API) to study servers.	up to 12 weeks

External Links

•   University of North Carolina Lineberger Comprehensive Cancer Center Clinical Trials