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

arXiv: https://arxiv.org/abs/2406.16252 · HTML: https://mlsanity.com/paper/2406.16252/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 24 Jun 2024.

## Builds on (most cited first, 12 of 12)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Conversational Health Agents: A Personalized LLM-Powered Agent Framework](https://mlsanity.com/paper/2310.02374/) (2023)
- [Health-LLM: Large Language Models for Health Prediction via Wearable Sensor Data](https://mlsanity.com/paper/2401.06866/) (2024)
- [The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models](https://mlsanity.com/paper/2309.06236/) (2023)
- [Towards a Personal Health Large Language Model](https://mlsanity.com/paper/2406.06474/) (2024)
- [ChatDiet: Empowering Personalized Nutrition-Oriented Food Recommender Chatbots through an LLM-Augmented Framework](https://mlsanity.com/paper/2403.00781/) (2024)
- [Transforming Wearable Data into Personal Health Insights using Large Language Model Agents](https://mlsanity.com/paper/2406.06464/) (2024)
- [Knowledge-Infused LLM-Powered Conversational Health Agent: A Case Study for Diabetes Patients](https://mlsanity.com/paper/2402.10153/) (2024)
- [Integrating Wearable Sensor Data and Self-reported Diaries for Personalized Affect Forecasting](https://mlsanity.com/paper/2403.13841/) (2024)
- [ZotCare: A Flexible, Personalizable, and Affordable mHealth Service Provider](https://mlsanity.com/paper/2307.01905/) (2023)
- [Zero-Shot Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2202.01924/) (2022)

## Built on by (most cited first, 3 of 3)

- [REMI: A Novel Causal Schema Memory Architecture for Personalized Lifestyle Recommendation Agents](https://mlsanity.com/paper/2509.06269/) (2025)
- [Personalized Counterfactual Framework: Generating Potential Outcomes from Wearable Data](https://mlsanity.com/paper/2508.14432/) (2025)
- [Personalized Causal Graph Reasoning for LLMs: An Implementation for Dietary Recommendations](https://mlsanity.com/paper/2503.00134/) (2025)

## Abstract (arXiv)

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.