# From Patient Consultations to Graphs: Leveraging LLMs for Patient Journey Knowledge Graph Construction

arXiv: https://arxiv.org/abs/2503.16533 · HTML: https://mlsanity.com/paper/2503.16533/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 21 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 6 of 6)

- [Multimodal Learning on Graphs for Disease Relation Extraction](https://mlsanity.com/paper/2203.08893/) (2022)
- [Robustly Extracting Medical Knowledge from EHRs: A Case Study of Learning a Health Knowledge Graph](https://mlsanity.com/paper/1910.01116/) (2019)
- [Patient-Centric Knowledge Graphs: A Survey of Current Methods, Challenges, and Applications](https://mlsanity.com/paper/2402.12608/) (2024)
- [Structured Extraction of Real World Medical Knowledge using LLMs for Summarization and Search](https://mlsanity.com/paper/2412.15256/) (2024)
- [Structural Quality Metrics to Evaluate Knowledge Graphs](https://mlsanity.com/paper/2211.10011/) (2022)
- [Patient Journey Ontology: Representing Medical Encounters for Enhanced Patient-Centric Applications](https://mlsanity.com/paper/2506.18772/) (2025)

## Abstract (arXiv)

The transition towards patient-centric healthcare necessitates a comprehensive understanding of patient journeys, which encompass all healthcare experiences and interactions across the care spectrum. Existing healthcare data systems are often fragmented and lack a holistic representation of patient trajectories, creating challenges for coordinated care and personalized interventions. Patient Journey Knowledge Graphs (PJKGs) represent a novel approach to addressing the challenge of fragmented healthcare data by integrating diverse patient information into a unified, structured representation. This paper presents a methodology for constructing PJKGs using Large Language Models (LLMs) to process and structure both formal clinical documentation and unstructured patient-provider conversations. These graphs encapsulate temporal and causal relationships among clinical encounters, diagnoses, treatments, and outcomes, enabling advanced temporal reasoning and personalized care insights. The research evaluates four different LLMs, such as Claude 3.5, Mistral, Llama 3.1, and Chatgpt4o, in their ability to generate accurate and computationally efficient knowledge graphs. Results demonstrate that while all models achieved perfect structural compliance, they exhibited variations in medical entity processing and computational efficiency. The paper concludes by identifying key challenges and future research directions. This work contributes to advancing patient-centric healthcare through the development of comprehensive, actionable knowledge graphs that support improved care coordination and outcome prediction.