Journal article
Feasibility study of an artificial intelligence chatbot-powered cognitive-behavioral lifestyle modification program
Annals of behavioral medicine, v 60(1), kaag038
01 Jan 2026
Abstract
Background Approximately 2 billion adults seek lifestyle modification to improve their health and well-being. However, because of cost and access barriers, only a tiny fraction receive gold-standard lifestyle modification programs led by trained coaches. Digital programs without human coaches are more disseminable but have limited efficacy. Recent advances in large language model (LLM) AI chatbots have the potential to revolutionize digital programs by emulating human coaches, offering a safe, low-cost, and scalable lifestyle modification intervention. Yet, no studies have developed and tested such a program. Purpose This study aims to evaluate the feasibility, safety, and user engagement of a new AI chatbot-powered lifestyle modification program named Lyra, which utilizes recent advances in LLM technology to potentially emulate the benefits of human coaching. Methods We developed Lyra, which integrates structured psychoeducational programming, digital tracking of health behaviors, and text messaging, all powered by an LLM engine. We tested the 8-week program, which included interactive training in behavioral strategies, customized meal plans, tailored feedback on goal progress, and on-demand coaching, with 17 participants in a sample of participants with overweight/obesity seeking lifestyle modification. Results The program was successfully implemented at a cost of $1.78/participant/week. Coders rated 2288 messages from and 475 conversations with Lyra. All were deemed safe, and the mean expertise was 8.5/10. Participants (mean BMI = 31.5) rated Lyra as helpful (69%), empathic (88%), and easy to use (94%); 88% valued having 24-h availability, and 75% developed a connection to Lyra. Participants initiated an average of 6.2 conversations, ranging from coping with cravings to unprompted “confessions” of having consumed unhealthy food. Conclusion This new form of intervention proved feasible, acceptable, safe, clinically adept, and capable of fostering a connection. However, rigorous testing of Lyra’s effectiveness is necessary.Lay Summary Billions of people around the world seek to improve their diet and exercise habits (“lifestyle modification” or lifestyle modification) in order to gain better health and quality of life. However, these changes are extremely hard to make, and existing digital programs are not effective. This study used newly available artificial intelligence (AI) to power a chatbot-based lifestyle modification program. The program, called Lyra, delivered lifestyle modification through text messages and incorporated features like goal setting, meal planning, and personalized advice based on digitally tracked physical activity, dietary, and weight data. Results from the study showed that most of the 17 participants found Lyra easy to use, engaging, and helpful in managing their lifestyle goals. They appreciated Lyra’s availability for support at any time, which traditional programs often lack. Additionally, participants felt a surprisingly strong connection to Lyra, highlighting the chatbot’s ability to offer empathy and support without judgment. Participants also demonstrated high usage of the program, for example, exchanging over 2000 messages with Lyra across the 8 weeks. Human lifestyle modification coaches reviewed Lyra’s messages and found them to display strong expertise. This research suggests that sophisticated AI chatbot interventions could be an accessible, affordable, and effective way to provide lifestyle management at a larger scale than is currently possible with in-person programs.
Metrics
1 Record Views
Details
- Title
- Feasibility study of an artificial intelligence chatbot-powered cognitive-behavioral lifestyle modification program
- Creators
- Evan M man (Corresponding Author) - Thomas Jefferson UniversityCharlotte J Hagerman - Oregon Research InstituteAsher E Hong - University of Illinois ChicagoZhuoran Huang - Northeastern UniversityHannah C McCausland - Drexel UniversityJasmine H Sun - Drexel UniversityLauren C Taylor - Drexel UniversityMeghan L Butryn - Drexel UniversityPreetha Chatterjee - Drexel UniversityRamtin Ehsani - Drexel UniversityNawal Syed - Drexel University
- Publication Details
- Annals of behavioral medicine, v 60(1), kaag038
- Publisher
- Oxford University Press
- Number of pages
- 11
- Resource Type
- Journal article
- Language
- English
- Academic Unit
- Psychological and Brain Sciences (Psychology); College of Medicine; Computer Science; College of Computing and Informatics; Center for Weight, Eating and Lifestyle Science (WELL) [Historical]
- Web of Science ID
- WOS:001816546800001
- Other Identifier
- 991022195561904721