Graph-Augmented LLMs for Personalized Health Insights: A Case Study in Sleep Analysis

TL;DR

This paper presents a graph-augmented LLM framework that enhances personalized health insights by effectively integrating complex, multi-dimensional wearable data, demonstrated through a sleep analysis case study with college students during COVID-19.

Contribution

The paper introduces a novel hierarchical graph-based approach to dynamically incorporate health data into LLM prompts, improving personalization and interpretability of health insights.

Findings

Significant improvements in relevance, comprehensiveness, actionability, and personalization of health insights.

Enhanced ability to generate tailored, actionable health advice from complex wearable data.

Demonstrated effectiveness in a sleep analysis case study with 20 college students.

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.