DKEC：面向诊断预测的领域知识增强多标签分类
DKEC: Domain Knowledge Enhanced Multi-Label Classification for Diagnosis Prediction
- University of Virginia（弗吉尼亚大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对医疗多标签分类的长尾标签分布问题，提出融合外部医疗知识构建异质图谱并结合标签级注意力的DKEC方法，在少样本类别上优于现有模型，还能让小模型达到大模型相当性能。
AI中文摘要：
医疗领域的多标签文本分类（MLTC）任务常面临标签分布长尾问题。已有研究探索利用层级标签结构为少样本类别挖掘相关信息，但大多未整合医疗指南中的外部知识。本文提出DKEC（领域知识增强分类）用于诊断预测，包含两项创新：（1）从外部资源自动构建异质知识图谱，以捕捉各类医疗实体间的语义关系；（2）通过标签级注意力机制将异质知识图谱融入少样本分类。我们利用三个在线医疗知识源构建DKEC，并在真实世界急救医疗服务（EMS）数据集与公开电子健康记录（EHR）数据集上进行评估。结果显示，DKEC的表现优于当前最优的标签级注意力网络及不同规模的transformer模型，尤其在少样本类别上优势显著。更重要的是，它能帮助小型语言模型达到与大语言模型相当的性能。
英文摘要：
Multi-label text classification (MLTC) tasks in the medical domain often face the long-tail label distribution problem. Prior works have explored hierarchical label structures to find relevant information for few-shot classes, but mostly neglected to incorporate external knowledge from medical guidelines. This paper presents DKEC, Domain Knowledge Enhanced Classification for diagnosis prediction with two innovations: (1) automated construction of heterogeneous knowledge graphs from external sources to capture semantic relations among diverse medical entities, (2) incorporating the heterogeneous knowledge graphs in few-shot classification using a label-wise attention mechanism. We construct DKEC using three online medical knowledge sources and evaluate it on a real-world Emergency Medical Services (EMS) dataset and a public electronic health record (EHR) dataset. Results show that DKEC outperforms the state-of-the-art label-wise attention networks and transformer models of different sizes, particularly for the few-shot classes. More importantly, it helps the smaller language models achieve comparable performance to large language models.
