Patient representation learning and interpretable evaluation using clinical notes

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.

Accepted manuscript at Journal of Biomedical Informatics

References in corpus (9)

• Efficient Estimation of Word Representations in Vector Space
• Distributed Representations of Words and Phrases and their Compositionality
• Teaching Machines to Read and Comprehend
• Understanding Neural Networks through Representation Erasure
• Clinical Intervention Prediction and Understanding using Deep Networks
• Neural Document Embeddings for Intensive Care Patient Mortality Prediction
• Combining LSTM and Latent Topic Modeling for Mortality Prediction
• The Use of Autoencoders for Discovering Patient Phenotypes
• Effective Representations of Clinical Notes

Cited by in corpus (7)

• Deep Representation Learning of Patient Data from Electronic Health Records (EHR): A Systematic Review
• SECNLP: A Survey of Embeddings in Clinical Natural Language Processing
• From Explainable to Interpretable Deep Learning for Natural Language Processing in Healthcare: How Far from Reality?
• Generalized and Transferable Patient Language Representation for Phenotyping with Limited Data
• ISeeU2: Visually Interpretable ICU mortality prediction using deep learning and free-text medical notes
• Hierarchical Semantic Correspondence Learning for Post-Discharge Patient Mortality Prediction
• A Study into patient similarity through representation learning from medical records