Classification of radiology reports using neural attention models
Authors:
- 1 May 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4363-4370
Abstract
The electronic health record (EHR) contains a large amount of multi-dimensional and unstructured clinical data of significant operational and research value. Distinguished from previous studies, our approach embraces a double-annotated dataset and strays away from obscure “black-box” models to comprehensive deep learning models. In this paper, we present a novel neural attention mechanism that not only classifies clinically important findings. Specifically, convolutional neural networks (CNN) with attention analysis are used to classify radiology head computed tomography reports based on five categories that radiologists would account for in assessing acute and communicable findings in daily practice. The experiments show that our CNN attention models outperform non-neural models, especially when trained on a larger dataset. Our attention analysis demonstrates the intuition behind the classifier's decision by generating a heatmap that highlights attended terms used by the CNN model; this is valuable when potential downstream medical decisions are to be performed by human experts or the classifier information is to be used in cohort construction such as for epidemiological studies.Keywords
All Related Versions
This publication has 23 references indexed in Scilit:
- Twitter Sentiment Analysis with Deep Convolutional Neural Networks2015
- Setting Value-Based Payment Goals — HHS Efforts to Improve U.S. Health CareNew England Journal of Medicine, 2015
- A New Initiative on Precision MedicineNew England Journal of Medicine, 2015
- N-gram support vector machines for scalable procedure and diagnosis classification, with applications to clinical free text data from the intensive care unitJournal of the American Medical Informatics Association, 2014
- A review of approaches to identifying patient phenotype cohorts using electronic health recordsJournal of the American Medical Informatics Association, 2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Convolutional Neural Networks for Sentence Classification2014
- Challenges in understanding clinical notes2013
- Convolution Neural Network for Relation Extraction2013
- Use of electronic health record data to evaluate overuse of cervical cancer screeningJournal of the American Medical Informatics Association, 2012