Clinical Report: Exploring the Role of Large Language Model–Based Conversational Agents

Overview

This scoping review examines the landscape of large language model (LLM)-driven conversational agents in cardiometabolic health. It identifies behavior change techniques (BCTs) utilized in these agents and assesses their delivery, transparency, and user experience.

Background

Cardiometabolic conditions are significant contributors to global morbidity and mortality, necessitating effective management strategies that extend beyond pharmacotherapy. Digital interventions, particularly LLM-driven conversational agents, offer scalable solutions for promoting sustained behavior change in self-management.

Data Highlights

No numerical data or trial results were provided in the source material.

Key Findings

• LLM-driven conversational agents can provide personalized lifestyle suggestions and simulate supportive coaching dialogues.
• Behavior Change Technique Taxonomy v1 (BCTTv1) can help identify the active ingredients in behavior change interventions.
• There is a fragmented evidence base regarding the effectiveness and implementation of LLM-driven agents in cardiometabolic care.
• Concerns exist regarding the accuracy and transparency of the content generated by these agents.

Clinical Implications

Clinicians and researchers should be aware of the potential and limitations of LLM-driven conversational agents in supporting cardiometabolic health.

Conclusion

The scoping review provides a structured overview of LLM-driven conversational agents in cardiometabolic care.

Related Resources & Content

1. Author(s)/Org, Source, Year -- Title
2. Author(s)/Org, Source, Year -- Title
3. Author(s)/Org, Source, Year -- Title
4. Author(s)/Org, Source, Year -- Title
5. American Diabetes Association, Diabetes Care, 2026 -- Facilitating Positive Health Behaviors and Well-being to Improve Health Outcomes
6. Author(s)/Org, Source, Year -- Title
7. American Medical Association, AMA, Year -- AMA policies to ensure AI supports—not replaces—physician judgment
8. 5. Facilitating Positive Health Behaviors and Well-being to Improve Health Outcomes: Standards of Care in Diabetes—2026 | Diabetes Care | American Diabetes Association
9. An AI-Powered Lifestyle Intervention vs Human Coaching in the Diabetes Prevention Program: A Randomized Clinical Trial | Trials | JAMA | JAMA Network
10. AMA policies to ensure AI supports—not replaces—physician judgment | American Medical Association