CLiGNet：临床标签交互图网络用于从临床转录中进行医学专科分类
CLiGNet: Clinical Label-Interaction Graph Network for Medical Specialty Classification from Clinical Transcriptions
AI总结：
本文提出CLiGNet，结合临床BERT与图卷积网络，解决医学专科分类中的数据泄露问题，通过标签图提升宏F1至0.279，验证了图结构对分类性能的显著提升。
摘要：
自动将临床转录分类到医学专科对于路由、编码和临床决策支持至关重要，但先前基于广泛使用的MTSamples基准的研究因在训练测试分割前应用SMOTE过采样导致严重的数据泄露。我们首先记录了这一方法学缺陷，并在40个医学专科（4966条记录）上建立了无泄漏基准，发现真实任务难度远高于此前报告。我们随后引入CLiGNet（临床标签交互图网络），一种结合Bio ClinicalBERT文本编码器和在由语义相似性和ICD 10章节先验构建的专科标签图上运行的双层图卷积网络。每个标签注意力门融合文档和标签图表示，通过聚焦二元交叉熵损失训练以处理极端类别不平衡（181:1）。在从TF-IDF分类器到临床Longformer的七个基线中，CLiGNet在无校准的情况下实现了最高的宏F1为0.279，消融研究证实GCN标签图提供了最大的单个组件增益（宏F1增加0.066）。添加每个标签Platt校准可获得预期校准误差0.007，展示了排名性能与概率可靠性之间的原则性权衡。我们提供了全面的失败分析，涵盖成对专科混淆、罕见类别行为、文档长度影响和令牌级集成梯度归因，为临床NLP系统部署提供可操作见解。
英文摘要：
Automated classification of clinical transcriptions into medical specialties is essential for routing, coding, and clinical decision support, yet prior work on the widely used MTSamples benchmark suffers from severe data leakage caused by applying SMOTE oversampling before train test splitting. We first document this methodological flaw and establish a leakage free benchmark across 40 medical specialties (4966 records), revealing that the true task difficulty is substantially higher than previously reported. We then introduce CLiGNet (Clinical Label Interaction Graph Network), a neural architecture that combines a Bio ClinicalBERT text encoder with a two layer Graph Convolutional Network operating on a specialty label graph constructed from semantic similarity and ICD 10 chapter priors. Per label attention gates fuse document and label graph representations, trained with focal binary cross entropy loss to handle extreme class imbalance (181 to 1 ratio). Across seven baselines ranging from TF IDF classifiers to Clinical Longformer, CLiGNet without calibration achieves the highest macro F1 of 0.279, with an ablation study confirming that the GCN label graph provides the single largest component gain (increase of 0.066 macro F1). Adding per label Platt scaling calibration yields an expected calibration error of 0.007, demonstrating a principled trade off between ranking performance and probability reliability. We provide comprehensive failure analysis covering pairwise specialty confusions, rare class behaviour, document length effects, and token level Integrated Gradients attribution, offering actionable insights for clinical NLP system deployment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
