AI-Optimized Weight Loss Treatment for Obesity

(ReLearn Trial)

Recruiting in Philadelphia (>99 mi)

Overseen By Rachel Shannon, BA

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Drexel University

Disqualifiers: Cancer, Type I diabetes, Psychosis, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 52 weeks

336 Participants Needed

Trial Summary

What is the purpose of this trial?

This trial is testing a smart computer program that helps people lose weight by giving them personalized advice. It tracks their progress and provides the best support based on individual responses. The goal is to see if this method is more effective and cheaper than traditional weight loss coaching.

Will I have to stop taking my current medications?

The trial does not specify if you need to stop taking your current medications. However, if you recently started or changed the dosage of a medication that affects weight, you may not be eligible to participate.

What data supports the effectiveness of the AI-optimized Behavioral Weight Loss Treatment for obesity?

Research shows that using artificial intelligence (AI) to optimize weight loss treatment can achieve similar weight loss results as traditional methods but with less time and cost. In a study, participants using AI required only one-third of the coaching time compared to standard treatment, yet experienced nearly the same weight loss. ^{1 2 3 4 5}

Is the AI-optimized weight loss treatment safe for humans?

The AI-optimized weight loss treatment has been tested in studies and found to be feasible and acceptable to participants, with no specific safety concerns reported. It uses artificial intelligence to adjust the intensity of interventions based on individual responses, aiming to achieve weight loss at a lower cost. ^{1 3 4 5 6}

How is the AI-optimized Behavioral Weight Loss Treatment different from other weight loss treatments?

The AI-optimized Behavioral Weight Loss Treatment uses artificial intelligence, specifically reinforcement learning, to tailor the intensity of weight loss interventions based on individual responses, reducing the need for frequent expert coaching while maintaining similar weight loss results at a lower cost. ^{4 5 6 7 8}

Research Team

Evan M Forman, PhD

Principal Investigator

Drexel University Center for Weight, Eating and Lifestyle Science

Eligibility Criteria

Adults aged 18-70 with a BMI of 27-50 kg/m², able to walk two city blocks and engage in remote weight loss programs using a smartphone. Excludes those with certain medical conditions, recent significant weight loss, or changes in medications affecting weight.

Inclusion Criteria

I am between 18 and 70 years old.

Individuals must also provide consent for the research team to contact their personal physician if necessary, to provide clearance or to consult about rapid weight loss

I can and will use a smartphone.

Exclusion Criteria

I recently started or changed the dose of a medication that may significantly affect my weight.

I have had weight loss surgery in the past.

I have lost more than 5% of my weight in the last 3 months.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive either a 1-year weekly gold standard behavioral weight loss remote group treatment or an AI-optimized treatment

52 weeks

Weekly remote sessions

Follow-up

Participants are monitored for safety and effectiveness after treatment

12 months

Treatment Details

Interventions

• AI-optimized Behavioral Weight Loss Treatment
• Standard Behavioral Weight Loss Treatment

Trial Overview Project ReLearn is comparing standard behavioral treatment for weight loss against an AI-optimized version that adapts weekly based on participant responses using mobile and wearable tech over one year.

Participant Groups

Group I: BWL-AI Experimental Treatment 1 Intervention

1 year of remote weight loss treatment made up of a combination of (1) remote small group-based behavioral weight loss sessions, (2) 12-minute individual video calls, (2) automated text messages. An MS-level clinician will deliver the group treatment. Most video calls will be delivered by a paraprofessional coach, but some by an MS-level clinician. Each week the AI system will select one of the interventions for each participant based on which treatment the participant has responded to the best, within certain time constraints.

Group II: BWL-S Active Control 1 Intervention

1 year of remote gold standard, small group-based behavioral weight loss treatment with an MS-level clinician.

Who Is Running the Clinical Trial?

Drexel University

Lead Sponsor

Trials

160

Recruited

48,600+

Findings from Research

In a study involving 468 adults with obesity, participants who switched to portion-controlled meals (PCM) after being identified as suboptimal responders to standard behavioral weight loss treatment (SBT) lost more weight at 6 months compared to those who switched to acceptance-based treatment (ABT), although the difference was not statistically significant.

Identifying suboptimal responders as early as Session 3 of treatment led to greater weight loss in those switched to PCM compared to those identified later, suggesting that early intervention may enhance the effectiveness of weight loss strategies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

BestFIT Sequential Multiple Assignment Randomized Trial Results: A SMART Approach to Developing Individualized Weight Loss Treatment Sequences. Sherwood, NE., Crain, AL., Seburg, EM., et al.[2022]

A study involving 154 overweight or obese patients showed that those referred to an automated Internet-based behavioral weight-loss intervention lost significantly more weight than those in an education-only control group, with average losses of 5.5 kg at 3 months and 5.4 kg at 6 months.

Over half of the participants in the Internet-based intervention achieved a clinically significant weight loss of 5% or more of their initial body weight, indicating the intervention's effectiveness in promoting weight control behaviors.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An automated internet behavioral weight-loss program by physician referral: a randomized controlled trial. Thomas, JG., Leahey, TM., Wing, RR.[2022]

A new study will evaluate whether a 12-month weight loss program using reinforcement learning (AI) can achieve similar weight loss results as traditional behavioral weight loss methods, but at a lower cost, involving 336 adults with overweight or obesity.

Preliminary results showed that participants using the AI system needed significantly less coaching while achieving nearly the same weight loss as those in the standard program, suggesting that AI could make weight loss support more accessible.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Using artificial intelligence to optimize delivery of weight loss treatment: Protocol for an efficacy and cost-effectiveness trial. Forman, EM., Berry, MP., Butryn, ML., et al.[2023]

A study involving 159 adults with overweight or obesity aims to optimize a smartphone-based intervention that delivers timely support to prevent dietary lapses during behavioral obesity treatment over a 6-month period.

Participants will receive tailored interventions based on their risk of dietary lapses, allowing for a more personalized approach to maintaining adherence to diet, with the goal of improving weight loss outcomes in future trials.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Optimizing a Just-in-Time Adaptive Intervention to Improve Dietary Adherence in Behavioral Obesity Treatment: Protocol for a Microrandomized Trial. Goldstein, SP., Zhang, F., Klasnja, P., et al.[2022]

The Opt-IN study, involving 562 adults with obesity, identified an effective weight-loss treatment package that included 12 coaching calls, buddy training, and primary care provider reports, resulting in an average weight loss of 6.1 kg for a cost of $427 per person.

By systematically evaluating treatment components, the study found that increasing coaching calls from 12 to 24 did not enhance weight loss, allowing for a more cost-effective and efficient obesity treatment strategy.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A Factorial Experiment to Optimize Remotely Delivered Behavioral Treatment for Obesity: Results of the Opt-IN Study. Spring, B., Pfammatter, AF., Marchese, SH., et al.[2021]

References

1. England pubmed.ncbi.nlm.nih.gov

BestFIT Sequential Multiple Assignment Randomized Trial Results: A SMART Approach to Developing Individualized Weight Loss Treatment Sequences. [2022]

2. Switzerland pubmed.ncbi.nlm.nih.gov

Predicting weight loss success on a new Nordic diet: an untargeted multi-platform metabolomics and machine learning approach. [2023]

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

An automated internet behavioral weight-loss program by physician referral: a randomized controlled trial. [2022]

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

Using artificial intelligence to optimize delivery of weight loss treatment: Protocol for an efficacy and cost-effectiveness trial. [2023]

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

Can the artificial intelligence technique of reinforcement learning use continuously-monitored digital data to optimize treatment for weight loss? [2020]

6. Canada pubmed.ncbi.nlm.nih.gov

The Use of Artificial Intelligence-Based Conversational Agents (Chatbots) for Weight Loss: Scoping Review and Practical Recommendations. [2022]

7. Canada pubmed.ncbi.nlm.nih.gov

Optimizing a Just-in-Time Adaptive Intervention to Improve Dietary Adherence in Behavioral Obesity Treatment: Protocol for a Microrandomized Trial. [2022]

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

A Factorial Experiment to Optimize Remotely Delivered Behavioral Treatment for Obesity: Results of the Opt-IN Study. [2021]