Piloting a Generative Artificial Intelligence Chatbot in a Mobile Weight Loss Program

Leveraging Generative Artificial Intelligence in Mobile Health Promotion Programs: A Use Case for Enhancing Tailored Messaging and Engagement in a Mobile Healthy Weight Program

The goal of this study is to learn if integrating a chatbot into an existing 12-week smartphone-delivered behavioral weight loss program is feasible and effective for weight loss among young adults. Researchers will compare a standard behavioral weight loss program for young adults that delivers 1-2 brief messages per day (AGILE) to the same program with a chatbot that offers additional behavior change support integrated into the app (AGILE + Chatbot) to determine if the program with the chatbot is feasible, acceptable to participants, and improves program engagement and weight change compared to AGILE alone.

Study Overview

• Status: Recruiting
• Conditions: Overweight and/or Obesity
• Intervention / Treatment: Behavioral: AGILE Intervention; Behavioral: Chatbot

Detailed Description

At baseline, 20 young adults, ages 18-39, with overweight or obesity, will be randomized to either the AGILE or AGILE + Chatbot group. Participants in both groups will receive a 12-week mobile behavioral weight loss intervention (AGILE) delivered via the study smartphone application. The weight loss intervention includes weekly evidence-based lessons; personalized goals; self-monitoring of diet, activity, and weight; weekly tailored feedback on progress; and brief, tailored messages 1-2 times per day displayed in the study smartphone app. Participants in the AGILE group will receive no additional program features. Participants in the AGILE + Chatbot group will have a version of the smartphone app with an integrated chatbot. The chatbot will be available for brief conversations 1-2 times per day. Assessments will occur at baseline and 12 weeks.

• Study Type: Interventional
• Enrollment (Estimated): 20
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Brooke T Nezami, PhD; Phone Number: 2 919-966-5852; Email: bnezami@unc.edu
• Study Contact Backup: Name: Karen Hatley, MPH; Phone Number: 2 919-966-5852; Email: keericks@email.unc.edu

Study Locations

• United States
  • North Carolina
    • Chapel Hill, North Carolina, United States, 27514
      • Recruiting
      • University of North Carolina at Chapel Hill
      • Principal Investigator: Deborah F Tate, PhD
      • Contact: Karen Hatley, MPH; Phone Number: 2 919-966-5852; Email: keericks@email.unc.edu
      • Principal Investigator: Brooke T Nezami, PhD
      • Principal Investigator: Carmina Valle, PhD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• body mass index (BMI) of 25-45 kg/m^2
• English-speaking and writing
• own an iPhone with a data plan
• willing to be randomized to either treatment group

Exclusion Criteria:

• Type 1 diabetes or currently receiving medical treatment for Type 2 diabetes
• Other health problems which may influence the ability to walk for physical activity or be associated with unintentional weight change, including tuberculosis, currently receiving cancer treatment, or history of a heart attack or stroke
• Report a heart condition, chest pain during periods of activity or rest, or loss of consciousness on the Physical Activity Readiness Questionnaire (PAR-Q; items 1-4), or report any other reason not able to walk for physical activity
• Lost 10 or more pounds (and kept it off) in the last 6 months
• Currently taking weight loss medications
• History of weight loss surgery or planning weight loss surgery in the next 4 months
• Report a past diagnosis of, or receiving treatment for, a DSM-5-TR (Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision) eating disorder (anorexia nervosa or bulimia nervosa)
• Currently pregnant or planning to become pregnant within the next 4 months
• Health or psychological diagnoses that preclude participation in a prescribed dietary and exercise program, including history of or diagnosis of schizophrenia or bipolar disorder, hospitalization for a psychiatric diagnosis in the past year, current diagnosis of alcohol or substance abuse
• Another member of the household is a participant or staff member on this trial
• Currently participating in a weight loss, nutrition, or physical activity study or program or other study that would interfere with this study
• Not willing to wear a Fitbit every day
• Have participated in another study conducted by the UNC Weight Research Program within the past 12 months

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Treatment
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Core Intervention; Participants receive the standard AGILE behavioral weight loss intervention via the study smartphone application.	Behavioral: AGILE Intervention; 12-week behavioral weight loss intervention that includes daily self-monitoring (tracking) of dietary intake, physical activity, and weight; personalized daily goals for dietary intake and physical activity; weekly behavioral lessons in the study app; weekly tailored feedback on goal progress and weight change; and 1-2 intervention messages per day that are tailored based on current diet, activity, and/or weight progress. Participants receive a Fitbit activity tracker and scale and track their activity and weight in the Fitbit app. Participants use a simplified approach to self-monitoring their dietary intake by tracking 'red' (high calorie) foods in the study's food log smartphone app. This data is used to inform the daily intervention messages and weekly tailored feedback.
Experimental: Core Intervention with Chatbot; Participants receive the standard AGILE behavioral weight loss intervention via the study smartphone application plus a chatbot integrated into the app.	Behavioral: AGILE Intervention; 12-week behavioral weight loss intervention that includes daily self-monitoring (tracking) of dietary intake, physical activity, and weight; personalized daily goals for dietary intake and physical activity; weekly behavioral lessons in the study app; weekly tailored feedback on goal progress and weight change; and 1-2 intervention messages per day that are tailored based on current diet, activity, and/or weight progress. Participants receive a Fitbit activity tracker and scale and track their activity and weight in the Fitbit app. Participants use a simplified approach to self-monitoring their dietary intake by tracking 'red' (high calorie) foods in the study's food log smartphone app. This data is used to inform the daily intervention messages and weekly tailored feedback.; Behavioral: Chatbot; The AGILE chatbot operates via a trained generative artificial intelligence large language model and offers additional support to participants for making changes in their dietary and physical activity behaviors. The chatbot is available for conversation only after a message has been delivered in the AGILE app. Participants can choose to start a conversation or not, and the ability to start a conversation expires at midnight. The chatbot is able to provide evidence-based cognitive behavioral support to participants including, but not limited to: 1) strategies and tips for dietary self-monitoring, physical activity tracking (wearing the Fitbit), and self-weighing; 2) overcoming common barriers to dietary and physical activity goal achievement; 3) general support for remaining engaged in behavior change efforts during the course of the program.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Program engagement	Program engagement is defined as the mean percent of days in which participants accessed the AGILE app.	up to 12 weeks
Chatbot engagement	Chatbot engagement is defined as the mean percent of days in which participants started a conversation with the chatbot.	up to 12 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Acceptability - Perceived usefulness of chatbot	Perceived usefulness (PU) of the chatbot is measured by the Perceived Usefulness subscale of the Technology Acceptance Model Questionnaire. This subscale includes four items that assess usefulness of the chatbot within the AGILE program that are scored on a Likert scale of 1 = Strongly disagree to 7 = Strongly agree. A composite score is calculated by taking an average of the four items. Higher values on the composite PU score represent a greater perceived usefulness of the chatbot.	12 weeks
Acceptability - Perceived ease of use of chatbot	Perceived ease of use (EU) of the chatbot is measured by the Perceived Ease of Use subscale of the Technology Acceptance Model Questionnaire. This subscale includes six items that assess how easy it is to use the chatbot within the AGILE program that are scored on a Likert scale of 1 = Strongly disagree to 7 = Strongly agree. A composite score is calculated by taking an average of the six items. Higher values on the composite EU score represent a greater perceived ease of use of the chatbot.	12 weeks
Percent weight change	Percent weight change is defined as weight change from baseline to 12 weeks, calculated as [(weight at 12 weeks - baseline weight) / baseline weight] × 100	Baseline, Week 12

Collaborators and Investigators

• Sponsor: University of North Carolina, Chapel Hill
• Collaborators: UNC Gillings School of Global Public Health
• Investigators: Principal Investigator: Brooke T Nezami, PhD, University of North Carolina, Chapel Hill

Study record dates

Study Major Dates

• Study Start (Actual): March 23, 2026
• Primary Completion (Estimated): July 13, 2026
• Study Completion (Estimated): July 20, 2026

Study Registration Dates

• First Submitted: April 9, 2026
• First Submitted That Met QC Criteria: April 9, 2026
• First Posted (Actual): April 16, 2026

Study Record Updates

• Last Update Posted (Actual): April 22, 2026
• Last Update Submitted That Met QC Criteria: April 16, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: Weight loss; Behavioral intervention; mHealth intervention
• Additional Relevant MeSH Terms: Body Weight; Body Weight Changes; Pathological Conditions, Signs and Symptoms; Signs and Symptoms; Weight Loss
• Other Study ID Numbers: 25-1638

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No