Journal
BIOINFORMATICS
Volume 36, Issue 21, Pages 5255-5261Publisher
OXFORD UNIV PRESS
DOI: 10.1093/bioinformatics/btaa668
Keywords
-
Categories
Funding
- Charite - Universitatsmedizin Berlin
- Berlin Institute of Health
- Deutsche Forschungsgemeinschaft (DFG) [SFB 1340/1 2018, 5943/31/41/91]
Ask authors/readers for more resources
Motivation: The development of deep, bidirectional transformers such as Bidirectional Encoder Representations from Transformers (BERT) led to an outperformance of several Natural Language Processing (NLP) benchmarks. Especially in radiology, large amounts of free-text data are generated in daily clinical workflow. These report texts could be of particular use for the generation of labels in machine learning, especially for image classification. However, as report texts are mostly unstructured, advanced NLP methods are needed to enable accurate text classification. While neural networks can be used for this purpose, they must first be trained on large amounts of manually labelled data to achieve good results. In contrast, BERT models can be pre-trained on unlabelled data and then only require fine tuning on a small amount of manually labelled data to achieve even better results. Results: Using BERT to identify the most important findings in intensive care chest radiograph reports, we achieve areas under the receiver operation characteristics curve of 0.98 for congestion, 0.97 for effusion, 0.97 for consolidation and 0.99 for pneumothorax, surpassing the accuracy of previous approaches with comparatively little annotation effort. Our approach could therefore help to improve information extraction from free-text medical reports.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available