Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Classification of Illness01:17

Classification of Illness

The meaning of illness is individualized to each person who experiences an alteration in health. In contrast, disease is a medical term indicating a pathological change in the structure and function of the body or mind. It is a condition that has specific symptoms and boundaries.
An illness is a response to a disease in which the person's level of functioning is changed compared with a previous level. The general classification of illness includes acute and chronic.
Acute illness is severe and...

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

The Effect of Mobile Health Intervention on Prelacteal Feeding Among Mothers in the First Month After Birth in South Ethiopia: A Cluster-Randomized Controlled Trial.

Nutrients·2026
Same author

Prognostic modeling in head and neck cancer: deep learning or handcrafted radiomics?

BJR artificial intelligence·2026
Same author

Understanding Clinicians' Informational Needs for AI-Driven Clinical Decision Support Systems: Qualitative Interview Study.

JMIR medical education·2026
Same author

An international multi-centre study to develop and validate federated learning-based prognostic models for anal cancer.

Nature communications·2026
Same author

Decoding Uncertainty Quantification for Oncology-An Illustration Using Radiomics.

Diagnostics (Basel, Switzerland)·2026
Same author

Knowledge Representation of a Multicenter Adolescent and Young Adult Cancer Infrastructure: Development of the STRONG AYA Knowledge Graph.

JCO clinical cancer informatics·2026

相关实验视频

Updated: May 11, 2026

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.6K

开发一款ICD-10编码助手:使用RoBERTa和GPT-4进行术语提取和基于描述的代码选择的试点研究.

Sander Puts1, Catharina M L Zegers1, Andre Dekker1

  • 1Department of Radiation Oncology (Maastro), GROW Research Institute for Oncology and Reproduction, Maastricht University Medical Centre+, P.O. Box 616, Maastricht, 6200 MD, Netherlands, 31 43 38 81863.

JMIR formative research
|February 12, 2025
PubMed
概括
此摘要是机器生成的。

这项研究探讨了用于ICD-10编码的AI,发现主要术语提取有希望,但基于RAG的代码分配效率较低. 未来的工作应该更好地使人工智能与医疗编码器工作流程保持一致,以提高准确性.

关键词:
人工智能自动化的AI自动化来自变压器的双向编码器表示在 GPT-4 中使用.在ICD-10中,它被命名为ICD-10.疾病的国际分类.在法学士 (LLM) 课程中.尼尔·内尔 (NER NER NER) 是一个国家.在RAG RAG的基础上.罗伯特·罗伯特是一个人.强大优化了BERT培训方法.人工智能的人工智能是人工智能.代码分析就是代码分析.编码 编码 编码 编码计算机辅助编码 计算机辅助编码计算机辅助编码是指计算机辅助编码.大型语言模型命名实体的认可 命名实体的认可提取增强生成的提取术语提取 提取 术语提取变压器模型变压器模型

更多相关视频

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

478

相关实验视频

Last Updated: May 11, 2026

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications
09:20

Cloud-Based Phrase Mining and Analysis of User-Defined Phrase-Category Association in Biomedical Publications

Published on: February 23, 2019

8.6K
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

478

科学领域:

  • 医疗信息学 医疗信息学
  • 医疗保健中的人工智能
  • 自然语言处理自然语言处理.

背景情况:

  • 世界卫生组织的国际疾病分类 (ICD) 为政策,研究和计费标准化了健康状况编码.
  • 目前医疗编码中的AI自动化显示出希望,但落后于人类的准确性,并且缺乏临床采用的解释性.

研究的目的:

  • 探索大型语言模型 (LLM) 的潜力,以协助医疗编码人员编码ICD-10.
  • 开发一种计算机辅助的编码系统,通过识别领先术语和使用检索增强生成 (RAG) 来增强人类编码者.

主要方法:

  • 利用CodiEsp-X数据集 (1000个西班牙临床病例具有ICD-10代码) 并通过使用GPT-4替换全文证据以领先术语来创建CodiEsp-X-lead.
  • 微调了一个强大优化的BERT预训练方法 (ROBERTa) 模型用于命名实体识别以提取领先条款.
  • 采用GPT-4来生成代码描述和RAG方法,使用OpenAI的文本嵌入-ada-002来通过矢量数据库分配ICD代码到领先的术语.

主要成果:

  • 微调的ROBERTa模型在CodiEsp-X-lead数据集上实现了ICD引项提取0.80的F1得分.
  • 由GPT-4生成的代码描述将RAG检索失败率降低约5%,用于诊断和程序.
  • 对于CodiEsp-X任务的整体可解释性F1得分为0.305,明显低于最先进的状态 (0.633),这是由于依赖描述和工作流失调的原因.

结论:

  • 主要术语提取显示出潜力,但基于RAG的代码分配使用GPT-4和描述被证明不那么有效.
  • 未来的研究必须更好地将人工智能与医疗编码器工作流程相结合,包括官方编码指南和字母表索引,以提高准确性和实际实用性.