Highly accurate classification of chest radiographic reports using a deep learning natural language model pre-trained on 3.8 million text reports
The DOI matches its Crossref record; 6 of the 6 references it cites were found in a registry or an index.
Abstract
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. Availability and implementation We make the source code for fine-tuning the BERT-models freely available at https://github.com/fast-raidiology/bert-for-radiology. Supplementary information: Supplementary data are available at Bioinformatics online.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126
Interrater reliability: The kappa statistic
McHugh, M. L. (2012) · Biochemia Medica · doi:10.11613/bm.2012.031 · Cited by 19,877
Artificial intelligence in radiology
Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. W. L. (2018) · Nature Reviews Cancer · doi:10.1038/s41568-018-0016-5 · Cited by 3,803
Potential Biases in Machine Learning Algorithms Using Electronic Health Record Data
Gianfrancesco, M. A., Tamang, S., Yazdany, J., & Schmajuk, G. (2018) · JAMA Internal Medicine · doi:10.1001/jamainternmed.2018.3763 · Cited by 1,395
Natural language processing in radiology: a systematic review
Pons, E., Braun, L. M. M., Hunink, M. G. M., & Kors, J. A. (2016) · Radiology · doi:10.1148/radiol.16142770 · Cited by 573
Deep Learning to Classify Radiology Free-Text Reports
Chen, M. C., Ball, R. L., Yang, L., Moradzadeh, N., Chapman, B. E., Larson, D. B., Langlotz, C. P., Amrhein, T. J., & Lungren, M. P. (2018) · Radiology · doi:10.1148/radiol.2017171115 · Cited by 217
Cited by
AMMU: A survey of transformer-based biomedical pretrained language models
Kalyan, K. S., Rajasekharan, A., & Sangeetha, S. (2022) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2021.103982 · Cited by 278
Banerjee, M., Chiew, D., Patel, K. T., Johns, I., Chappell, D., Linton, N., Cole, G. D., Francis, D. P., Szram, J., Ross, J., et al. (2021) · BMC Medical Education · doi:10.1186/s12909-021-02870-x · Cited by 168
He, K., Mao, R., Lin, Q., Ruan, Y., Lan, X., Feng, M., & Cambria, E. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.102963 · Cited by 147
He, K., Mao, R., Lin, Q., Ruan, Y., Lan, X., Feng, M., & Cambria, E. (2024) · doi:10.2139/ssrn.4809363 · Cited by 69
Metadata
- Authors
- Bressem, K. K., Adams, L. C., Gaudin, R. A., Tröltzsch, D., Hamm, B., Makowski, M. R., Schüle, C.-Y., Vahldiek, J. L., & Niehues, S. M.
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2020-07-23
- Volume
- 36
- Issue
- 21
- Pages
- 5255-5261
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- OpenAlex
- W3045332379
- Cited by
- 69
- References
- 6
- FWCI
- 3.98
- Type
- journal article
- Language
- en
- Open access
- closed
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Highly accurate classification of chest radiographic reports using a deep learning natural language model pre-trained on 3.8 million text reports. https://app.cochat.ai/papers/10.1093/bioinformatics/btaa668
- The paper
- Bressem, K. K., Adams, L. C., Gaudin, R. A., Tröltzsch, D., Hamm, B., Makowski, M. R., Schüle, C.-Y., Vahldiek, J. L., & Niehues, S. M. (2021). Highly accurate classification of chest radiographic reports using a deep learning natural language model pre-trained on 3.8 million text reports. Bioinformatics. https://doi.org/10.1093/bioinformatics/btaa668
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.