REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation

• URL: http://arxiv.org/abs/2609.04415v1
• Date: Thu, 03 Sep 2026 19:29:22 GMT
• Title: REFINE: LLM Refinement over Budgeted Text-Attributed Graphs for Personalized Medical Concept Representation
• Abstract summary: REFINE is a KG-aware budgeted graph refinement framework for patient-personalized medical concept encoding.<n> REFINE consistently improves diverse EHR backbones, outperforms strong baselines, and demonstrates robust gains across component ablation, KG selection, and data insufficiency.
• Score: 12.878616211892115
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Learning rich medical concept representations is essential for EHR prediction. Text-attributed knowledge graphs (TKGs) provide a natural foundation by organizing heterogeneous medical relations together with textual semantics. However, most existing encoders process concepts uniformly across patients, despite the fact that a code's meaning and predictive value depend on patient-specific clinical context and trajectory. Learning patient-personalized concept representations from TKGs introduces two key challenges: (1) deciding how much KG context to incorporate for each observed code, and (2) aligning semantic information with the patient-specific relational structure. We propose REFINE, a KG-aware budgeted LLM graph refinement framework for patient-personalized medical concept encoding. Starting from a global TKG, REFINE constructs patient-specific temporal graphs. A sequential reinforcement learning policy selects a personalized KG expansion budget for each observed code. The resulting patient graph is processed by a heterogeneous GNN to capture relation-aware structural dependencies, while a frozen LLM uses graph-aware soft prompts to semantically refine concept representations. Experiments on MIMIC-III and MIMIC-IV show that REFINE consistently improves diverse EHR backbones, outperforms strong baselines, and demonstrates robust gains across component ablation, KG selection, and data insufficiency.

Related papers

• Multimodal Graph-based Classification of Esophageal Motility Disorders [73.90451172929117]
  Diagnosing esophageal motility disorders pose significant challenges due to the complexity of high-resolution impedance manometry data and variability in clinical interpretation.<n>This work explores the feasibility of a multimodal Machine Learning-based classification approach that combines HRIM recordings with patient-specific information and incorporates a graph-based modeling of esophageal physiology.
  arXiv  Detail & Related papers  (2026-05-13T14:52:12Z)
• Text-Attributed Knowledge Graph Enrichment with Large Language Models for Medical Concept Representation [14.711294299248024]
  We present CoMed, an LLM-empowered graph learning framework for medical concept representation.<n>CoMed first builds a global knowledge graph (KG) over medical codes by combining statistically reliable associations mined from EHRs with type-constrained LLM.<n>It then utilizes LLMs to enrich the KG into a text-attributed graph by generating node descriptions and edge rationales.<n>Finally, CoMed jointly trains a LoRA-tuned LLaMA text encoder with a heterogeneous GNN, fusing text semantics and graph structure into unified concept embeddings.
  arXiv  Detail & Related papers  (2026-04-14T22:29:18Z)
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging [67.74482877175797]
  MIRNet is a novel framework that integrates self-supervised pre-training with constrained graph-based reasoning.<n>We introduce TongueAtlas-4K, a benchmark comprising 4,000 images annotated with 22 diagnostic labels.
  arXiv  Detail & Related papers  (2025-11-13T06:30:41Z)
• From Patient Consultations to Graphs: Leveraging LLMs for Patient Journey Knowledge Graph Construction [3.0874677990361246]
  Patient Journey Knowledge Graphs (PJKGs) represent a novel approach to addressing the challenge of fragmented healthcare data.<n>PJKGs process and structure both formal clinical documentation and unstructured patient-provider conversations.<n>These graphs encapsulate temporal and causal relationships among clinical encounters, diagnoses, treatments, and outcomes.
  arXiv  Detail & Related papers  (2025-03-18T14:44:28Z)
• Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval [61.70489848327436]
  KARE is a novel framework that integrates knowledge graph (KG) community-level retrieval with large language models (LLMs) reasoning.<n>Extensive experiments demonstrate that KARE outperforms leading models by up to 10.8-15.0% on MIMIC-III and 12.6-12.7% on MIMIC-IV for mortality and readmission predictions.
  arXiv  Detail & Related papers  (2024-10-06T18:46:28Z)
• REALM: RAG-Driven Enhancement of Multimodal Electronic Health Records Analysis via Large Language Models [19.62552013839689]
  Existing models often lack the medical context relevent to clinical tasks, prompting the incorporation of external knowledge. We propose REALM, a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR representations. Our experiments on MIMIC-III mortality and readmission tasks showcase the superior performance of our REALM framework over baselines.
  arXiv  Detail & Related papers  (2024-02-10T18:27:28Z)
• Multi-modal Graph Learning over UMLS Knowledge Graphs [1.6311327256285293]
  We propose a novel approach named Multi-Modal UMLS Graph Learning (MMUGL) for learning meaningful representations of medical concepts. These representations are aggregated to represent entire patient visits and then fed into a sequence model to perform predictions at the granularity of multiple hospital visits of a patient.
  arXiv  Detail & Related papers  (2023-07-10T10:16:57Z)
• Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation [92.73584302508907]
  We propose a knowledge graph with Dynamic structure and nodes to facilitate medical report generation with Contrastive Learning. In detail, the fundamental structure of our graph is pre-constructed from general knowledge. Each image feature is integrated with its very own updated graph before being fed into the decoder module for report generation.
  arXiv  Detail & Related papers  (2023-03-18T03:53:43Z)
• Semantic Decomposition Improves Learning of Large Language Models on EHR Data [0.0]
  H-BERT ingests complete graph tree expansions of hierarchical medical codes as opposed to only ingesting the leaves and pushes patient-level labels down to each visit. This methodology significantly improves prediction of patient membership in over 500 medical diagnosis classes as measured by aggregated AUC and APS.
  arXiv  Detail & Related papers  (2022-11-14T14:59:16Z)
• MIMO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning [49.57261599776167]
  We propose an end-to-end robust Transformer-based solution, Mutual Integration of patient journey and Medical Ontology (MIMO) for healthcare representation learning and predictive analytics.
  arXiv  Detail & Related papers  (2021-07-20T07:04:52Z)
• BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes [53.163089893876645]
  We propose a novel self-attention mechanism that captures the contextual dependency and temporal relationships within a patient's healthcare journey. An end-to-end bidirectional temporal encoder network (BiteNet) then learns representations of the patient's journeys. We have evaluated the effectiveness of our methods on two supervised prediction and two unsupervised clustering tasks with a real-world EHR dataset.
  arXiv  Detail & Related papers  (2020-09-24T00:42:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.