A Keyword-Enhanced Approach to Handle Class Imbalance in Clinical Text Classification

Recent applications ofdeep learning have shown promising results for classifying unstructured text in the healthcare domain. However, the reliability of models in production settings has been hindered by imbalanced data sets in which a small subset of the classes dominate. In the absence of adequate...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of biomedical and health informatics 2022-06, Vol.26 (6), p.2796-2803
Main Authors: Blanchard, Andrew E., Gao, Shang, Yoon, Hong-Jun, Christian, J. Blair, Durbin, Eric B., Wu, Xiao-Cheng, Stroup, Antoinette, Doherty, Jennifer, Schwartz, Stephen M., Wiggins, Charles, Coyle, Linda, Penberthy, Lynne, Tourassi, Georgia D.
Format: Article
Language:English
Subjects:
Cancer
Classification
Constraint modelling
Data Collection
Electronic mail
Histopathology
Humans
Identification methods
Impact analysis
Keywords
Machine learning
medical information systems
Model accuracy
natural language processing
Production
Reproducibility of Results
Task analysis
Training
Training data
Unstructured data
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recent applications ofdeep learning have shown promising results for classifying unstructured text in the healthcare domain. However, the reliability of models in production settings has been hindered by imbalanced data sets in which a small subset of the classes dominate. In the absence of adequate training data, rare classes necessitate additional model constraints for robust performance. Here, we present a strategy for incorporating short sequences of text (i.e. keywords) into training to boost model accuracy on rare classes. In our approach, we assemble a set of keywords, including short phrases, associated with each class. The keywords are then used as additional data during each batch of model training, resulting in a training loss that has contributions from both raw data and keywords. We evaluate our approach on classification of cancer pathology reports, which shows a substantial increase in model performance for rare classes. Furthermore, we analyze the impact of keywords on model output probabilities for bigrams, providing a straightforward method to identify model difficulties for limited training data.
ISSN:2168-2194
2168-2208
2168-2208
DOI:10.1109/JBHI.2022.3141976