Currently submitted to: JMIR Formative Research
Date Submitted: Apr 3, 2025
Open Peer Review Period: Apr 14, 2025 - Jun 9, 2025
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
From Barriers to Tactics: Development Study of Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching
ABSTRACT
Background:
Effective management of cardiometabolic conditions requires sustained positive nutrition habits, often hindered by complex and individualized barriers. Direct human management is simply not scalable, while deterministic automated approaches to nutrition coaching may lack the personalization needed to address these diverse challenges.
Objective:
We report the development and validation of a novel large language model (LLM)-powered agentic workflow designed to provide personalized nutrition coaching by directly identifying and mitigating patient-specific barriers.
Methods:
We used behavioral science principles to create a comprehensive workflow that can map nutrition-related barriers to corresponding evidence-based strategies. First, a specialized LLM agent intentionally probes for and identifies root causes of a patient’s dietary struggles. Subsequently, a separate LLM agent delivers tailored tactics designed to overcome those specific barriers. We conducted a user study with individuals with cardiometabolic conditions (N=16) to inform our workflow design and then validated our approach through an additional user study (n=6). We also conducted a large-scale simulation study, grounding on real patient vignettes and expert-validated metrics, where human experts evaluated the system’s performance across multiple scenarios and domains.
Results:
In our user study, the system accurately identified barriers and provided personalized guidance. Five out of 6 participants agreed that the LLM agent helped them recognize obstacles preventing them from being healthier, and all participants strongly agreed that the advice felt personalized to their situation. In our simulation study, experts agreed that the LLM agent accurately identified primary barriers in more than 90% of cases. Additionally, experts determined that the workflow delivered personalized and actionable tactics empathetically, with average ratings of 4.17-4.79 on a 5-point Likert scale.
Conclusions:
Our findings demonstrate the potential of this LLM-powered agentic workflow to improve nutrition coaching by providing personalized, scalable, and behaviorally-informed interventions. Clinical Trial: NA
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.