Publication
Title
Patient representation learning and interpretable evaluation using clinical notes
Author
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.
Language
English
Source (journal)
Journal of biomedical informatics. - New York
Journal of biomedical informatics. - New York
Publication
New York : 2018
ISSN
1532-0464
Volume/pages
84 (2018) , p. 103-113
ISI
000445054800010
Pubmed ID
29966746
Full text (Publisher's DOI)
Full text (open access)
Full text (publisher's version - intranet only)
UAntwerpen
Faculty/Department
Research group
Project info
ACCUMULATE: Acquiring crucial medical information using language technology.
Publication type
Subject
Affiliation
Publications with a UAntwerp address
External links
Web of Science
Record
Identification
Creation 23.07.2018
Last edited 20.09.2021
To cite this reference