多模态双编码器检索用于自动ICD编码
Multimodal Dual-Encoder Retrieval for Automated ICD Coding
浏览论文内容
中文总结 AI 辅助
针对现有ICD编码方法无法处理多模态数据、难以扩展且缺乏透明度的问题，提出两阶段框架，先以多模态双编码器门控融合检索候选，再用LLM重排序，实验证明其优于密集多标签分类基线。
中文摘要 AI 辅助
准确的国际疾病分类（ICD）编码对于大规模临床研究、文档记录和计费至关重要。当前ICD预测方法存在三个主要问题：（1）由于它们依赖于结构化电子健康记录（EHR）数据或非结构化临床笔记，因此无法理解多模态患者数据。（2）它们在扩展到更多ICD代码（ICD-9中有9K+个代码）方面也存在困难，因为传统分类器需要密集输出层，并且通常不能很好地泛化到长尾罕见疾病。（3）它们缺乏临床使用的透明度。为解决这些挑战，本研究提出一个两阶段框架，首先使用多模态双编码器检索模型检索ICD代码，其中通过门控融合整合结构化与非结构化患者数据。第二阶段使用基于大语言模型（LLM）的重排序器对前k个检索候选进行细化，提供带有临床相关解释的排序代码。我们的实验表明，所提出的方法在多模态双融合分类器基线上提高了Micro-F1和精确率。这些改进表明，将门控多模态检索系统与基于LLM的重排序相结合，是自动ICD编码中密集多标签分类的一种实用替代方案。
英文摘要
Accurate International Classification of Diseases (ICD) coding is crucial for large-scale clinical research, documentation, and billing. There are three primary problems with current ICD prediction methods: (1) They are unable to comprehend multimodal patient data because they rely on either structured EHR data or unstructured clinical notes. (2) They also struggle with scalability to a larger amount of ICD codes (9K+ codes in ICD-9), as traditional classifiers need dense output layers and often do not generalize well to long tail rare diseases. (3) They lack transparency for clinical use. To address these challenges, this research proposes a two-stage framework that first retrieves ICD codes using a multimodal dual-encoder retrieval model, where structured and unstructured patient data are integrated through gated fusion. The second stage refines the top-k retrieved candidates with an LLM-based re-ranker that provides ranked codes with clinically relevant explanations. Our experiments show that the proposed approach improves Micro-F1 and Precision over a multimodal dual-fusion classifier baseline. These improvements demonstrate that combining a gated multimodal retrieval system with LLM-based re-ranking is a practical alternative to dense multi-label classification for automated ICD coding.
发表机构
- Amazon（亚马逊）
- Rutgers University（罗格斯大学）
机构由 AI 辅助整理，请以论文原文为准。
