This paper is in the following e-collection/theme issue:

Computer-Aided Diagnosis (255) Breast Cancer (293) Medical imaging (116) Imaging Informatics (308) Generative Language Models Including ChatGPT (725) AI Language Models in Health Care (208)

Published on in Vol 13 (2025)

Preprints (earlier versions) of this paper are available at https://preprints.jmir.org/preprint/80182, first published .
Performance of ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1 in BI-RADS Category 4 Classification and Malignancy Prediction From Mammography Reports: Retrospective Diagnostic Study

Performance of ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1 in BI-RADS Category 4 Classification and Malignancy Prediction From Mammography Reports: Retrospective Diagnostic Study

Performance of ChatGPT-4o, Claude 3 Opus, and DeepSeek-R1 in BI-RADS Category 4 Classification and Malignancy Prediction From Mammography Reports: Retrospective Diagnostic Study

Authors of this article:

Xingwei Dai1 Author Orcid Image ;   Man Ke1 Author Orcid Image ;   Dixing Xie1 Author Orcid Image ;   Mengting Mei1 Author Orcid Image ;   Si Wei1 Author Orcid Image ;   Yi Dai1 Author Orcid Image ;   Ronghua Yan1, 2 Author Orcid Image
Article Authors Cited by Tweetations Metrics

Xingwei Dai   1 * , MS ;   Man Ke   1 * , MS ;   Dixing Xie   1 , MS ;   Mengting Mei   1 , BS ;   Si Wei   1 , BS ;   Yi Dai   1 , PhD ;   Ronghua Yan   1, 2 , PhD

1 Peking University Shenzhen Hospital, Shenzhen, China

2 Southern University of Science and Technology, Shenzhen, China

*these authors contributed equally

Corresponding Author: