EUVIMEDEUVIMED entdecken
ValidierungsstudieOpen Access

A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching: Development and Validation Study

Eric Yang iD, Tomas Garcia iD, Hannah G Williams iD, Bhawesh Kumar iD, Martin Ramé iD, Eileen Rivera iD, Yiran Ma iD, Jonathan Amar iD, Caricia Catalani iD, Yugang Jia iD

JMIR Formative Research · 2025

DOI: 10.2196/75421 ↗

Kurz gefasst

Validierungsstudie in der Zeitschrift JMIR Formative Research, 2025. Verfasst von Eric Yang und 9 weiteren Autor:innen. Beteiligte Einrichtung: Verily Life Sciences, 2999 Olympus Blvd, Ste 1000, Dallas, TX, 75019, United States, 1 650-495-7100. Hauptthemen laut MEDLINE: Workflow, Mentoring, Behavioral Sciences, Precision Medicine. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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, and 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 to intentionally probe for and identify root causes of a patient’s dietary struggles. Subsequently, a separate LLM agent to deliver tailored tactics that were 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 (27 or 28/30). 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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WorkflowMentoringBehavioral SciencesPrecision MedicineHumansMaleFemaleAdultMiddle AgedReproducibility of Results

Stichwörter der Autor:innen

LLMbehavioral sciencelarge language modelnutritional coaching

Autor:innen und Institutionen

  • Verily Life Sciences, 2999 Olympus Blvd, Ste 1000, Dallas, TX, 75019, United States, 1 650-495-7100.

ORCID-Profile: Eric Yang, Tomas Garcia, Hannah G Williams, Bhawesh Kumar, Martin Ramé, Eileen Rivera, Yiran Ma, Jonathan Amar, Caricia Catalani, Yugang Jia

Zitieren

APA

Yang, E., Garcia, T., Williams, H. G., Kumar, B., Ramé, M., Rivera, E., Ma, Y., Amar, J., Catalani, C., & Jia, Y. (2025). A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching: Development and Validation Study. JMIR Formative Research. https://doi.org/10.2196/75421

Vancouver

Yang E, Garcia T, Williams HG, Kumar B, Ramé M, Rivera E, et al. A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching: Development and Validation Study. JMIR Formative Research. 2025. doi:10.2196/75421

BibTeX
@article{Yang2025,
  author = {Yang, Eric and Garcia, Tomas and Williams, Hannah G and Kumar, Bhawesh and Ramé, Martin and Rivera, Eileen and Ma, Yiran and Amar, Jonathan and Catalani, Caricia and Jia, Yugang},
  title = {A Behavioral Science-Informed Agentic Workflow for Personalized Nutrition Coaching: Development and Validation Study},
  journal = {JMIR Formative Research},
  year = {2025},
  doi = {10.2196/75421}
}
Kostenlos starten →