验证就是你所需要的:为零射击临床编码提示大型语言模型。

IF 6.8 2区 医学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Shaoxin Li, Can Zheng, Jiaxiang Wu, Qinwei Xu, Xingkun Xu, Hanyang Wang, Yingkai Sun, Zhian Bai, Yuchen Xu, Lifeng Zhu, Weiguo Hu, Feiyue Huang
{"title":"验证就是你所需要的:为零射击临床编码提示大型语言模型。","authors":"Shaoxin Li, Can Zheng, Jiaxiang Wu, Qinwei Xu, Xingkun Xu, Hanyang Wang, Yingkai Sun, Zhian Bai, Yuchen Xu, Lifeng Zhu, Weiguo Hu, Feiyue Huang","doi":"10.1109/JBHI.2025.3593028","DOIUrl":null,"url":null,"abstract":"<p><p>Clinical coding translates medical information from Electronic Health Records (EHRs) into structured codes such as ICD-10, which are essential for healthcare applications. Advances in deep learning and natural language processing have enabled automatic ICD coding models to achieve notable accuracy metrics on in-domain datasets when adequately trained. However, the scarcity of clinical medical texts and the variability across different datasets pose significant challenges, making it difficult for current state-of-the-art models to ensure robust generalization performance across diverse data distributions. Recent advances in Large Language Models (LLMs), such as GPT-4o, have shown great generalization capabilities across general domains and potential in medical information processing tasks. However, their performance in generating clinical codes remains suboptimal. In this study, we propose a novel ICD coding paradigm based on code verification to leverage the capabilities of LLMs. Instead of directly generating accurate codes from a vast code space, we simplify the task by verifying the code assignment from a given candidate set. Through extensive experiments, we demonstrate that LLMs function more effectively as code verifiers rather than code generators, with GPT-4o achieving the best performance on the CodiEsp dataset under zero-shot settings. Furthermore, our results indicate that LLM-based systems can perform on par with state-of-the-art clinical coding systems while offering superior generalizability across institutions, languages, and ICD versions.</p>","PeriodicalId":13073,"journal":{"name":"IEEE Journal of Biomedical and Health Informatics","volume":"PP ","pages":""},"PeriodicalIF":6.8000,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Verification is All You Need: Prompting Large Language Models for Zero-Shot Clinical Coding.\",\"authors\":\"Shaoxin Li, Can Zheng, Jiaxiang Wu, Qinwei Xu, Xingkun Xu, Hanyang Wang, Yingkai Sun, Zhian Bai, Yuchen Xu, Lifeng Zhu, Weiguo Hu, Feiyue Huang\",\"doi\":\"10.1109/JBHI.2025.3593028\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Clinical coding translates medical information from Electronic Health Records (EHRs) into structured codes such as ICD-10, which are essential for healthcare applications. Advances in deep learning and natural language processing have enabled automatic ICD coding models to achieve notable accuracy metrics on in-domain datasets when adequately trained. However, the scarcity of clinical medical texts and the variability across different datasets pose significant challenges, making it difficult for current state-of-the-art models to ensure robust generalization performance across diverse data distributions. Recent advances in Large Language Models (LLMs), such as GPT-4o, have shown great generalization capabilities across general domains and potential in medical information processing tasks. However, their performance in generating clinical codes remains suboptimal. In this study, we propose a novel ICD coding paradigm based on code verification to leverage the capabilities of LLMs. Instead of directly generating accurate codes from a vast code space, we simplify the task by verifying the code assignment from a given candidate set. Through extensive experiments, we demonstrate that LLMs function more effectively as code verifiers rather than code generators, with GPT-4o achieving the best performance on the CodiEsp dataset under zero-shot settings. Furthermore, our results indicate that LLM-based systems can perform on par with state-of-the-art clinical coding systems while offering superior generalizability across institutions, languages, and ICD versions.</p>\",\"PeriodicalId\":13073,\"journal\":{\"name\":\"IEEE Journal of Biomedical and Health Informatics\",\"volume\":\"PP \",\"pages\":\"\"},\"PeriodicalIF\":6.8000,\"publicationDate\":\"2025-07-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"IEEE Journal of Biomedical and Health Informatics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1109/JBHI.2025.3593028\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"COMPUTER SCIENCE, INFORMATION SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Journal of Biomedical and Health Informatics","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1109/JBHI.2025.3593028","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

摘要

临床编码将电子健康记录(EHRs)中的医疗信息转换为结构化代码,如ICD-10,这对医疗保健应用程序至关重要。深度学习和自然语言处理的进步使自动ICD编码模型在经过充分训练的情况下,能够在域内数据集上实现显着的准确性指标。然而,临床医学文本的稀缺性和不同数据集之间的可变性构成了重大挑战,使得当前最先进的模型难以确保跨不同数据分布的鲁棒泛化性能。大型语言模型(LLMs)的最新进展,如gpt - 40,已经显示出跨一般领域的强大泛化能力和在医疗信息处理任务中的潜力。然而,它们在生成临床代码方面的性能仍然不够理想。在这项研究中,我们提出了一种新的基于代码验证的ICD编码范式,以利用llm的能力。我们不是直接从庞大的代码空间中生成准确的代码,而是通过验证给定候选集的代码分配来简化任务。通过广泛的实验,我们证明llm作为代码验证器而不是代码生成器更有效,gpt - 40在零射击设置下在CodiEsp数据集上实现了最佳性能。此外,我们的研究结果表明,基于法学硕士的系统可以与最先进的临床编码系统相提并论,同时提供跨机构、语言和ICD版本的优越通用性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Verification is All You Need: Prompting Large Language Models for Zero-Shot Clinical Coding.

Clinical coding translates medical information from Electronic Health Records (EHRs) into structured codes such as ICD-10, which are essential for healthcare applications. Advances in deep learning and natural language processing have enabled automatic ICD coding models to achieve notable accuracy metrics on in-domain datasets when adequately trained. However, the scarcity of clinical medical texts and the variability across different datasets pose significant challenges, making it difficult for current state-of-the-art models to ensure robust generalization performance across diverse data distributions. Recent advances in Large Language Models (LLMs), such as GPT-4o, have shown great generalization capabilities across general domains and potential in medical information processing tasks. However, their performance in generating clinical codes remains suboptimal. In this study, we propose a novel ICD coding paradigm based on code verification to leverage the capabilities of LLMs. Instead of directly generating accurate codes from a vast code space, we simplify the task by verifying the code assignment from a given candidate set. Through extensive experiments, we demonstrate that LLMs function more effectively as code verifiers rather than code generators, with GPT-4o achieving the best performance on the CodiEsp dataset under zero-shot settings. Furthermore, our results indicate that LLM-based systems can perform on par with state-of-the-art clinical coding systems while offering superior generalizability across institutions, languages, and ICD versions.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
IEEE Journal of Biomedical and Health Informatics
IEEE Journal of Biomedical and Health Informatics COMPUTER SCIENCE, INFORMATION SYSTEMS-COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
CiteScore
13.60
自引率
6.50%
发文量
1151
期刊介绍: IEEE Journal of Biomedical and Health Informatics publishes original papers presenting recent advances where information and communication technologies intersect with health, healthcare, life sciences, and biomedicine. Topics include acquisition, transmission, storage, retrieval, management, and analysis of biomedical and health information. The journal covers applications of information technologies in healthcare, patient monitoring, preventive care, early disease diagnosis, therapy discovery, and personalized treatment protocols. It explores electronic medical and health records, clinical information systems, decision support systems, medical and biological imaging informatics, wearable systems, body area/sensor networks, and more. Integration-related topics like interoperability, evidence-based medicine, and secure patient data are also addressed.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信