May 25, 2022Open Access

Application of a Domain-specific BERT for Detection of Speech Recognition Errors in Radiology Reports

Key Points

Key points are not available for this paper at this time.

Abstract

Radiology-specific BERT models fine-tuned on generated errors were able to identify SR errors in radiology reports and suggest corrections.Keywords: Computer Applications, Technology Assessment Supplemental material is available for this article. © RSNA, 2022See also the commentary by Abajian and Cheung in this issue.

Read Full Paperexternally

Bookmark

View Full Paper

Cite This Study

Chaudhari et al. (Wed,) studied this question.

synapsesocial.com/papers/69d99b2e2a25b240b7a3cfb0 https://doi.org/https://doi.org/10.1148/ryai.210185

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

1Improving Radiology Report Quality by Rapidly Notifying Radiologist of Report Errors2015 · 36 citations
2Machine learning and natural language processing methods to identify ischemic stroke, acuity and location from radiology reports2020 · 105 citations
3Speech Recognition in the Radiology Department: A Systematic Review2015 · 40 citations
4BioBERT: a pre-trained biomedical language representation model for biomedical text mining2019 · 7,033 citations
5Bert model fine-tuning for text classification in knee OA radiology reports2020 · 5 citations

Bookmark

View Full Paper