用Mamba增强的疾病语义知识图表用于可解释的自动ICD编码
Pengli Lu1, Chao Dong1, Jingjin Xue1
1School of Computer and Artificial Intelligence, Lanzhou University of Technology, Lanzhou 730050, Gansu, China.
Journal of biomedical informatics
|December 24, 2025
概括
一个新的AI框架MKHCNet通过整合知识图和先进的深度学习来增强国际疾病分类 (ICD) 的自动编码. 这提高了电子健康记录的准确性和可解释性.
科学领域:
- 人工智能的人工智能
- 医疗信息学 医疗信息学
- 计算语言学 计算语言学
背景情况:
- 自动ICD编码利用AI来简化电子健康记录 (EHR) 的疾病分类.
- 当前的深度学习模型面临的挑战是语义不一致,标签模糊性和实际EHR数据的有限解释性.
- 现有的方法很难捕捉复杂的关系,并提供透明的决策过程.
研究的目的:
- 引入MKHCNet,这是一个旨在克服自动ICD编码局限性的新型框架.
- 通过集成的知识表示,远程依赖模型和对比规范化来提高编码性能.
- 提高AI驱动的ICD编码系统的可解释性和临床适用性.
主要方法:
- 开发了MKHCNet,将疾病语义知识图用于丰富的标签表示.
- 利用Mamba网络进行跨域依赖建模,并使用ContraNorm来改善标签分离性.
- 实现了层次位置标签注意 (HPLA) 以实现细粒度的解释性,以及FastKAN与RBF用于分类.
主要成果:
- 在基准数据集 (MIMIC-FULL,MIMIC-50) 上,MKHCNet表现出优异的性能,在MIMIC-FULL上提高了MaAUC2.1%,P@8提高了0.3%.
- 该模型有效地捕获了EHR数据中的复杂非线性关系.
- 案例研究证实了该模型能够识别复杂的语义线索,并提供强大的临床解释性.
结论:
- MKHCNet代表了自动ICD编码的重大进步,解决了准确性和可解释性的关键挑战.
- 知识图和新型深度学习模块的集成增强了模型处理复杂临床数据的能力.
- 拟议的框架为在医疗保健中开发更可靠,更透明的AI工具提供了一个有希望的方向.
更多相关视频
05:47Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
1.2K
06:55Inverse Probability of Treatment Weighting Propensity Score using the Military Health System Data Repository and National Death Index
Published on: January 8, 2020
15.0K
相关概念视频
01:17Classification of Illness
8.5K
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...
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...
8.5K
01:11Genome-wide Association Studies-GWAS
15.2K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
GWAS does not require the identification of the target gene involved in...
15.2K