Graph-Augmented LLMs for Personalized Health Insights: A Case Study in Sleep Analysis
Ajan Subramanian, Zhongqi Yang, Iman Azimi, Amir M. Rahmani
TL;DR
This work addresses the challenge of extracting personalized health insights from multi-dimensional wearable data by augmenting LLM prompts with a hierarchical inter- and intra-patient similarity graph and random-forest-derived feature-importance scores. The proposed graph-augmented LLM framework combines an NLP engine, RAG-backed data retrieval, and an insight-generation LLM to produce context-rich, patient-specific recommendations. Validation is performed on a sleep analysis case study with 20 college students during the COVID-19 lockdown, using a secondary LLM to evaluate outputs on relevance, comprehensiveness, actionability, and personalization, with notable gains when comparing similar/dissimilar days and including feature importance. The approach demonstrates improved, tailored health insights and suggests future extensions with Graph Neural Networks to further enhance real-time interpretation and decision support in wearable-health contexts.
Abstract
Health monitoring systems have revolutionized modern healthcare by enabling the continuous capture of physiological and behavioral data, essential for preventive measures and early health intervention. While integrating this data with Large Language Models (LLMs) has shown promise in delivering interactive health advice, traditional methods like Retrieval-Augmented Generation (RAG) and fine-tuning often fail to fully utilize the complex, multi-dimensional, and temporally relevant data from wearable devices. These conventional approaches typically provide limited actionable and personalized health insights due to their inadequate capacity to dynamically integrate and interpret diverse health data streams. In response, this paper introduces a graph-augmented LLM framework designed to significantly enhance the personalization and clarity of health insights. Utilizing a hierarchical graph structure, the framework captures inter and intra-patient relationships, enriching LLM prompts with dynamic feature importance scores derived from a Random Forest Model. The effectiveness of this approach is demonstrated through a sleep analysis case study involving 20 college students during the COVID-19 lockdown, highlighting the potential of our model to generate actionable and personalized health insights efficiently. We leverage another LLM to evaluate the insights for relevance, comprehensiveness, actionability, and personalization, addressing the critical need for models that process and interpret complex health data effectively. Our findings show that augmenting prompts with our framework yields significant improvements in all 4 criteria. Through our framework, we can elicit well-crafted, more thoughtful responses tailored to a specific patient.