MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph

• URL: http://arxiv.org/abs/2508.12393v2
• Date: Tue, 19 Aug 2025 05:18:31 GMT
• Title: MedKGent: A Large Language Model Agent Framework for Constructing Temporally Evolving Medical Knowledge Graph
• Authors: Duzhen Zhang, Zixiao Wang, Zhong-Zhi Li, Yahan Yu, Shuncheng Jia, Jiahua Dong, Haotian Xu, Xing Wu, Yingying Zhang, Tielin Zhang, Jie Yang, Xiuying Chen, Le Song,
• Abstract summary: We introduce MedKGent, a framework for constructing temporally evolving medical Knowledge Graphs.<n>We simulate the emergence of biomedical knowledge via a fine-grained daily time series.<n>The resulting KG contains 156,275 entities and 2,971,384 relational triples.
• Score: 57.54231831309079
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The rapid expansion of medical literature presents growing challenges for structuring and integrating domain knowledge at scale. Knowledge Graphs (KGs) offer a promising solution by enabling efficient retrieval, automated reasoning, and knowledge discovery. However, current KG construction methods often rely on supervised pipelines with limited generalizability or naively aggregate outputs from Large Language Models (LLMs), treating biomedical corpora as static and ignoring the temporal dynamics and contextual uncertainty of evolving knowledge. To address these limitations, we introduce MedKGent, a LLM agent framework for constructing temporally evolving medical KGs. Leveraging over 10 million PubMed abstracts published between 1975 and 2023, we simulate the emergence of biomedical knowledge via a fine-grained daily time series. MedKGent incrementally builds the KG in a day-by-day manner using two specialized agents powered by the Qwen2.5-32B-Instruct model. The Extractor Agent identifies knowledge triples and assigns confidence scores via sampling-based estimation, which are used to filter low-confidence extractions and inform downstream processing. The Constructor Agent incrementally integrates the retained triples into a temporally evolving graph, guided by confidence scores and timestamps to reinforce recurring knowledge and resolve conflicts. The resulting KG contains 156,275 entities and 2,971,384 relational triples. Quality assessments by two SOTA LLMs and three domain experts demonstrate an accuracy approaching 90%, with strong inter-rater agreement. To evaluate downstream utility, we conduct RAG across seven medical question answering benchmarks using five leading LLMs, consistently observing significant improvements over non-augmented baselines. Case studies further demonstrate the KG's value in literature-based drug repurposing via confidence-aware causal inference.

Related papers

• Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation [97.36081721024728]
  We propose the first benchmark for assessing confidence in multi-turn interaction during realistic medical consultations.<n>Our benchmark unifies three types of medical data for open-ended diagnostic generation.<n>We present MedConf, an evidence-grounded linguistic self-assessment framework.
  arXiv  Detail & Related papers  (2026-01-22T04:51:39Z)
• Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval [29.377256313893934]
  Large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge.<n>LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge.<n>We propose GHAR, a underlinegenerative underlinehierarchical underlineagentic underlineRAG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare.
  arXiv  Detail & Related papers  (2025-11-17T12:15:46Z)
• MedSeqFT: Sequential Fine-tuning Foundation Models for 3D Medical Image Segmentation [55.37355146924576]
  MedSeqFT is a sequential fine-tuning framework for medical image analysis.<n>It adapts pre-trained models to new tasks while refining their representational capacity.<n>It consistently outperforms state-of-the-art fine-tuning strategies.
  arXiv  Detail & Related papers  (2025-09-07T15:22:53Z)
• Data Overdose? Time for a Quadruple Shot: Knowledge Graph Construction using Enhanced Triple Extraction [0.0]
  The rapid expansion of publicly-available medical data presents a challenge for clinicians and researchers alike.<n>This paper presents an approach to information extraction and automatic knowledge graph generation to identify and connect biomedical knowledge.
  arXiv  Detail & Related papers  (2025-08-05T13:30:41Z)
• Uncertainty-Driven Expert Control: Enhancing the Reliability of Medical Vision-Language Models [52.2001050216955]
  Existing methods aim to enhance the performance of Medical Vision Language Model (MedVLM) by adjusting model structure, fine-tuning with high-quality data, or through preference fine-tuning.<n>We propose an expert-in-the-loop framework named Expert-Controlled-Free Guidance (Expert-CFG) to align MedVLM with clinical expertise without additional training.
  arXiv  Detail & Related papers  (2025-07-12T09:03:30Z)
• MedGemma Technical Report [75.88152277443179]
  We introduce MedGemma, a collection of medical vision-language foundation models based on Gemma 3 4B and 27B.<n>MedGemma demonstrates advanced medical understanding and reasoning on images and text.<n>We additionally introduce MedSigLIP, a medically-tuned vision encoder derived from SigLIP.
  arXiv  Detail & Related papers  (2025-07-07T17:01:44Z)
• Agentic Medical Knowledge Graphs Enhance Medical Question Answering: Bridging the Gap Between LLMs and Evolving Medical Knowledge [6.977177904883792]
  AMG-RAG is a framework that automates the construction and continuous updating of medical knowledge graphs.<n>It integrates reasoning, and retrieves current external evidence, such as PubMed and WikiSearch.<n>It achieves an F1 score of 74.1 percent on MEDQA and an accuracy of 66.34 percent on MEDMCQA, outperforming both comparable models and those 10 to 100 times larger.
  arXiv  Detail & Related papers  (2025-02-18T16:29:45Z)
• KGARevion: An AI Agent for Knowledge-Intensive Biomedical QA [31.080514888803886]
  KGARevion is a knowledge graph-based agent that answers knowledge-intensive questions.<n>It generates relevant triplets by leveraging the latent knowledge embedded in a large language model.<n>It then verifies these triplets against a grounded knowledge graph, filtering out errors and retaining only accurate, contextually relevant information.
  arXiv  Detail & Related papers  (2024-10-07T00:17:37Z)
• 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)
• EMERGE: Enhancing Multimodal Electronic Health Records Predictive Modeling with Retrieval-Augmented Generation [22.94521527609479]
  EMERGE is a Retrieval-Augmented Generation (RAG) driven framework to enhance multimodal EHR predictive modeling.<n>We extract entities from time-series data and clinical notes by prompting Large Language Models (LLMs) and align them with professional PrimeKG.<n>The extracted knowledge is then used to generate task-relevant summaries of patients' health statuses.
  arXiv  Detail & Related papers  (2024-05-27T10:53:15Z)

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.