Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health
This addresses the challenge of making sleep health advice feasible and adaptive for individuals using wearables, though it is incremental as it builds on existing chatbot and data-driven methods.
The authors tackled the problem of translating sleep-tracking data into actionable improvements by developing HealthGuru, an LLM-powered chatbot that provides personalized sleep health recommendations, resulting in improved sleep duration, activity scores, and user motivation compared to a baseline in an eight-week study with 16 participants.
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.