arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.03244cs.CLcs.AI
收藏

预测任务中临床笔记的注意分析

An Analysis of Attention over Clinical Notes for Predictive Tasks

Northeastern University(东北大学)

Sarthak Jain, Ramin Mohammadi, Byron C. Wallace

摘要:

向电子医疗记录(EMR)的转变引发了对机器学习和自然语言技术的研究,以分析患者记录,并从这些感兴趣的临床结果中进行预测。两个观察激发了我们的目标。首先,EMR中包含的非结构化注释通常包含关键信息,因此应该由模型利用。其次,虽然强大的预测性能很重要,但模型的可解释性对于这一领域的应用来说可能同样重要。总之,这些观点表明,EMR的神经模型可能会受益于将注意力纳入笔记,人们可能希望这既能提高性能,又能提供预测的透明度。在这项工作中,我们使用两个EMR语料库和四个不同的预测任务进行实验来探索这个问题,即:(i)包含注意力机制对于在音符字段上操作的神经编码器模块至关重要,以产生竞争性性能,但是,(ii)不幸的是,虽然这些提高了预测性能,但它们是否为预测提供有意义的支持显然不太清楚。

英文摘要:

The shift to electronic medical records (EMRs) has engendered research into machine learning and natural language technologies to analyze patient records, and to predict from these clinical outcomes of interest. Two observations motivate our aims here. First, unstructured notes contained within EMR often contain key information, and hence should be exploited by models. Second, while strong predictive performance is important, interpretability of models is perhaps equally so for applications in this domain. Together, these points suggest that neural models for EMR may benefit from incorporation of attention over notes, which one may hope will both yield performance gains and afford transparency in predictions. In this work we perform experiments to explore this question using two EMR corpora and four different predictive tasks, that: (i) inclusion of attention mechanisms is critical for neural encoder modules that operate over notes fields in order to yield competitive performance, but, (ii) unfortunately, while these boost predictive performance, it is decidedly less clear whether they provide meaningful support for predictions.

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。

↑