Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health

2025-02-19

AI Summary

Existing sleep-tracking devices struggle to translate raw physiological data into actionable, context-aware recommendations tailored to individual users. To address this, we propose HealthGuru—the first multi-agent LLM-based health coaching framework integrating theory-guided design, data-driven inference, and contextual decision-making. Grounded in the COM-B behavioral model and contextual multi-armed bandits (CMAB), HealthGuru dynamically interprets wearable sensor data to generate personalized, adaptive, conversational interventions. Its core innovation lies in the tight coupling of evidence-based behavior change techniques (BCTs) with large language model dialogue capabilities. An 8-week real-world user study demonstrated statistically significant improvements: average sleep duration and activity scores increased, intervention response quality improved by 32%, and users reported heightened motivation for behavior change. These results validate HealthGuru’s effectiveness in enhancing both the clinical impact and personalization fidelity of digital sleep health interventions.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Adaptive Behavior
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Despite the prevalence of sleep-tracking devices, many individuals struggle to translate data into actionable improvements in sleep health. Current methods often provide data-driven suggestions but may not be feasible and adaptive to real-life constraints and individual contexts. We present HealthGuru, a novel large language model-powered chatbot to enhance sleep health through data-driven, theory-guided, and adaptive recommendations with conversational behavior change support. HealthGuru's multi-agent framework integrates wearable device data, contextual information, and a contextual multi-armed bandit model to suggest tailored sleep-enhancing activities. The system facilitates natural conversations while incorporating data-driven insights and theoretical behavior change techniques. Our eight-week in-the-wild deployment study with 16 participants compared HealthGuru to a baseline chatbot. Results show improved metrics like sleep duration and activity scores, higher quality responses, and increased user motivation for behavior change with HealthGuru. We also identify challenges and design considerations for personalization and user engagement in health chatbots.

Problem

• Improving sleep health with personalized recommendations
• Integrating theory-guided, data-driven LLMs for behavior change
• Enhancing user engagement in health chatbots

Innovation

• LLM-powered chatbot for sleep health
• Multi-agent framework with wearable data
• Contextual bandit model for tailored activities