Patient representation learning and interpretable evaluation using clinical notes

TL;DR

This paper investigates learning dense, task-independent patient representations from clinical notes using autoencoders and paragraph vectors, evaluating their transferability and interpretability across multiple clinical prediction tasks.

Contribution

It introduces a method for learning transferable patient representations from clinical notes and proposes techniques for their interpretability, demonstrating advantages over traditional sparse representations.

Findings

Dense representations outperform sparse ones with limited data.

Medical concept-based features do not improve classification performance.

Novel interpretability techniques identify influential features in patient representations.

Abstract

We have three contributions in this work: 1. We explore the utility of a stacked denoising autoencoder and a paragraph vector model to learn task-independent dense patient representations directly from clinical notes. To analyze if these representations are transferable across tasks, we evaluate them in multiple supervised setups to predict patient mortality, primary diagnostic and procedural category, and gender. We compare their performance with sparse representations obtained from a bag-of-words model. We observe that the learned generalized representations significantly outperform the sparse representations when we have few positive instances to learn from, and there is an absence of strong lexical features. 2. We compare the model performance of the feature set constructed from a bag of words to that obtained from medical concepts. In the latter case, concepts represent problems, treatments, and tests. We find that concept identification does not improve the classification performance. 3. We propose novel techniques to facilitate model interpretability. To understand and interpret the representations, we explore the best encoded features within the patient representations obtained from the autoencoder model. Further, we calculate feature sensitivity across two networks to identify the most significant input features for different classification tasks when we use these pretrained representations as the supervised input. We successfully extract the most influential features for the pipeline using this technique.