揭示临床文本分类模型解释方法的三大缺陷，推动更可靠的医疗AI解释
Challenges in Explaining Pretrained Clinical Text Classifiers
- 针对医院住院时长预测任务，测试了现有解释方法
- 发现解释结果过度关注无意义词汇、不稳定且对混乱输入仍自信
- 强调需开发语义合理、抗语言噪声的临床可解释性方案
在临床自然语言处理中，解释神经网络模型的预测仍是重大挑战，尤其面对长篇非结构化医学文本。尽管事后解释方法如LIME和SHAP被广泛使用，但在临床叙述场景下常表现不佳。本文通过在医院住院时长预测任务上的针对性演示，揭示了基于词元和扰动的解释技术的核心局限：对非信息性词元过度强调、归因结果不稳定，以及对语义混乱输入仍给出高置信度预测。这些发现凸显了开发具有临床意义、语义基础且对语言噪声鲁棒的解释策略的必要性。
原文摘要 · Abstract (English)
Explaining the predictions of neural models in clinical NLP remains a significant challenge, especially for complex tasks involving long, unstructured medical texts. While post-hoc methods like LIME and SHAP are widely used, they often fall short when applied to clinical narratives. In this paper, we identify core limitations of token-level and perturbation-based explanation techniques through targeted demonstra- tions on a hospital length-of-stay prediction task. Our findings reveal issues such as overemphasis on non-informative tokens, instability in at- tributions, and high-confidence predictions for incoherent input variants. These results underscore the need for explanation strategies that are clin- ically meaningful, semantically grounded, and robust to linguistic noise.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。