Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Pengcheng, Xiao, Cao, Jiang, Minhao, Bhatia, Parminder, Kass-Hout, Taha, Sun, Jimeng, Han, Jiawei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915250692947968
author Jiang, Pengcheng
Xiao, Cao
Jiang, Minhao
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
author_facet Jiang, Pengcheng
Xiao, Cao
Jiang, Minhao
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
contents Large language models (LLMs) have demonstrated significant potential in clinical decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual medical knowledge, limiting their high-stake healthcare applications such as clinical diagnosis. Traditional retrieval-augmented generation (RAG) methods attempt to address these limitations but frequently retrieve sparse or irrelevant information, undermining prediction accuracy. We introduce KARE, a novel framework that integrates knowledge graph (KG) community-level retrieval with LLM reasoning to enhance healthcare predictions. KARE constructs a comprehensive multi-source KG by integrating biomedical databases, clinical literature, and LLM-generated insights, and organizes it using hierarchical graph community detection and summarization for precise and contextually relevant information retrieval. Our key innovations include: (1) a dense medical knowledge structuring approach enabling accurate retrieval of relevant information; (2) a dynamic knowledge retrieval mechanism that enriches patient contexts with focused, multi-faceted medical insights; and (3) a reasoning-enhanced prediction framework that leverages these enriched contexts to produce both accurate and interpretable clinical predictions. 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. In addition to its impressive prediction accuracy, our framework leverages the reasoning capabilities of LLMs, enhancing the trustworthiness of clinical predictions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_04585
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
Jiang, Pengcheng
Xiao, Cao
Jiang, Minhao
Bhatia, Parminder
Kass-Hout, Taha
Sun, Jimeng
Han, Jiawei
Computation and Language
Large language models (LLMs) have demonstrated significant potential in clinical decision support. Yet LLMs still suffer from hallucinations and lack fine-grained contextual medical knowledge, limiting their high-stake healthcare applications such as clinical diagnosis. Traditional retrieval-augmented generation (RAG) methods attempt to address these limitations but frequently retrieve sparse or irrelevant information, undermining prediction accuracy. We introduce KARE, a novel framework that integrates knowledge graph (KG) community-level retrieval with LLM reasoning to enhance healthcare predictions. KARE constructs a comprehensive multi-source KG by integrating biomedical databases, clinical literature, and LLM-generated insights, and organizes it using hierarchical graph community detection and summarization for precise and contextually relevant information retrieval. Our key innovations include: (1) a dense medical knowledge structuring approach enabling accurate retrieval of relevant information; (2) a dynamic knowledge retrieval mechanism that enriches patient contexts with focused, multi-faceted medical insights; and (3) a reasoning-enhanced prediction framework that leverages these enriched contexts to produce both accurate and interpretable clinical predictions. 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. In addition to its impressive prediction accuracy, our framework leverages the reasoning capabilities of LLMs, enhancing the trustworthiness of clinical predictions.
title Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval
topic Computation and Language
url https://arxiv.org/abs/2410.04585