Tag: RAG
-
Evaluation Strategies for LLM-Based Exercise and Health Coaching: A Scoping Review
Introduction Large language models (LLMs) promise to transform exercise and health coaching by delivering personalized training plans, real-time feedback, and motivational support. Yet translating this potential into safe, effective practice requires rigorous evaluation that can handle multimodal inputs—text reports, video-based posture analysis, and physiological sensor data—while ensuring safety and personalization. This scoping review maps the…
-
Enhancing Cardiovascular Nutrition Guidance with Retrieval-Augmented LLMs: A Cross-Sectional Evaluation
Introduction As digital health tools proliferate, large language models (LLMs) and retrieval-augmented generation (RAG) offer promise for delivering accessible, guideline-based nutrition information aimed at preventing cardiovascular disease (CVD). This cross-sectional study investigates how different model architectures perform in providing nutrition guidance aligned with American Heart Association (AHA) recommendations, and whether grounding LLMs in vetted guidelines…
-
Evaluating LLMs and Retrieval-Augmented Generation for Guideline-Adherent Cardiovascular Nutrition Guidance
Introduction: Digital Diet Guidance Meets Cardiovascular Health As digital health tools proliferate, large language models (LLMs) and retrieval-augmented generation (RAG) offer promising avenues to deliver scalable, guideline-based nutrition information for cardiovascular disease (CVD) prevention. Grounded in the American Heart Association’s (AHA) dietary recommendations, these technologies aim to translate complex nutrition science into accessible advice that…