English(EN) LTR-ICD: A Ranking-Aware Framework for Automatic ICD Coding

新框架改进了自动ICD代码分配和排序

作者 PulseAugur 编辑部 · [1 个来源] · 2026-08-24 04:00

研究人员开发了LTR-ICD，一个用于从临床笔记中自动分配和排序诊断代码的新型框架。与之前的基于分类的方法不同，LTR-ICD将问题视为一个检索任务，考虑了ICD代码的基本顺序。这种方法显著提高了主要诊断代码识别的准确性，排名准确率达到47%，而最先进的分类器为20%。该框架还展示了卓越的分类性能，微平均F1得分为0.6065，宏平均F1得分为0.2904。 AI

影响该框架可以提高医疗编码的准确性和效率，可能改善医疗管理和报销流程。

排序理由该集群包含一篇详细介绍自动ICD编码新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CL 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍自动ICD编码新框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, product; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 64 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CL TIER_1 English(EN) · Mohammad Mansoori, Amira Soliman, Farzaneh Etminani · 2026-08-24 04:00

LTR-ICD：一个感知排序的自动ICD编码框架

arXiv:2510.13922v2 Announce Type: replace-cross Abstract: Clinical notes contain unstructured text provided by clinicians during patient encounters. These notes are usually accompanied by a sequence of diagnostic codes following the International Classification of Diseases (ICD).…

本文如何被排名

报道来源 [1]

LTR-ICD：一个感知排序的自动ICD编码框架

相关实体

相关话题