We have two main contributions in this work: 1. We explore the usage of a
stacked denoising autoencoder, and a paragraph vector model to learn
task-independent dense patient representations directly from clinical notes. We
evaluate these representations by using them as features in multiple supervised
setups, and compare their performance with those of sparse representations. 2.
To understand and interpret the representations, we explore the best encoded
features within the patient representations obtained from the autoencoder
model. Further, we calculate the significance of the input features of the
trained classifiers when we use these pretrained representations as input.

使用自编码器模型和段落向量模型，直接从医学记录中学习任务无关的密集病人信息，比较与稀疏表示方法的表现，并利用编码的特征进行解释和筛选

从临床笔记中的无监督患者表征得出可解释的分类决策

Unsupervised patient representations from clinical notes with  interpretable classification decisions

We study the problem of attributing the prediction of a deep network to its
input features, a problem previously studied by several other works. We
identify two fundamental axioms---Sensitivity and Implementation Invariance
that attribution methods ought to satisfy. We show that they are not satisfied
by most known attribution methods, which we consider to be a fundamental
weakness of those methods. We use the axioms to guide the design of a new
attribution method called Integrated Gradients. Our method requires no
modification to the original network and is extremely simple to implement; it
just needs a few calls to the standard gradient operator. We apply this method
to a couple of image models, a couple of text models and a chemistry model,
demonstrating its ability to debug networks, to extract rules from a network,
and to enable users to engage with models better.

本文研究了深度网络输入特征对预测的影响，提出了敏感性和实现不变性两个公理，并指出大部分已知的边缘归因方法并不满足这两个公理。最后，作者设计了一种不需要修改原始网络的全新边缘归因方法 —— 集成梯度，并将其应用于图像、文本和化学模型中。结果表明，该方法不仅具有调试和提取规则的功能，还能够有效地帮助用户更好地使用模型。