arXiv cs.AI· Jifan Gao, Junjie Hu, John Caskey, Madeline Oguss, Simona Cristea, Anoop Mayampurath, Matthew Churpek, Majid Afshar, Guanhua Chen·· 3 小时前AI 评分33
无需概念监督的 Token-Concept Attention 临床文本预测可解释框架
A Concept-Based Interpretable Framework for Clinical Text-based Prediction via Token-Concept Attention without Concept Supervision
AI 导读
研究者提出一种基于概念的可解释临床文本预测框架，通过定制的 cross-attention 瓶颈结构，无需人工概念标注即可识别概念相关性并用于线性预测层。该框架在胸部创伤严重程度分层（私有数据集）和院内死亡率预测（MIMIC-III）两项任务中，AUROC 与对应黑盒模型差距在 0.02 以内，并支持队列级与患者级解释。
正文 · 原文
Abstract:Objective: Concept-based interpretation has emerged as a promising approach for explaining blackbox models using human-understandable, high-level concepts. However, most existing methods require annotated concept labels to train the model to identify concepts in the input, and obtaining such annotations in clinical text is often expensive. This study aims to enable concept-based interpretation for language models without concept supervision on clinical prediction tasks. Methods: We propose a novel framework that enables concept-based interpretation without concept supervision through a tailored cross-attention bottleneck. Clinical text and the text descriptions of medical concepts are first tokenized and embedded by a pretrained language model. A cross-attention module then estimates the presence of each concept for each text token, producing concept relevance scores that capture how concepts are involved throughout the note. These scores are pooled and used in a linear prediction layer to model clinical outcomes in an interpretable manner. Results: The performance of the proposed framework was compared against blackbox models across two tasks: chest trauma severity stratification using a private dataset and an in-hospital mortality prediction task using the publicly available MIMIC-III dataset. The proposed framework achieved AUROC values within 0.02 of the corresponding blackbox models. The framework also enabled cohort- and patient-level interpretation, capturing the overall concept importance across the cohort and patient-specific concept contributions. Conclusion: Our proposed framework realizes concept-based interpretation without requiring ground-truth concept presence labels. It improves the transparency of clinical text predictions while maintaining strong performance in clinical prediction tasks.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.13564 [cs.CL] |
| (or arXiv:2611.13564v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2611.13564 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jifan Gao [view email]
[v1]
Tue, 10 Nov 2026 04:31:25 UTC (1,211 KB)
来源：arXiv cs.AI · arxiv.org