Benchmarking a deep learning model against healthcare practitioners for hip fracture detection in the emergency department
The DL model could not match radiographers' performance, highlighting the importance of clinical context in fracture detection. While the model's short reading time could reduce diagnostic delays, further development incorporating higher-resolution images and multimodal clinical data integration is needed before clinical deployment.
Authors
- Jared Jue Ying Yeo
- Siang Hiong Goh (ORCID: https://orcid.org/0000-0002-7657-9472)
- Yan Gao (ORCID: https://orcid.org/0000-0003-4279-1595)
- Yet Yen Yan (ORCID: https://orcid.org/0000-0002-5537-8575)
- Jin Tan (ORCID: https://orcid.org/0000-0003-1849-4865)
- Hong Choon Oh
Institutions
- Singapore General Hospital (SG)
- Mount Elizabeth Hospital (SG)
- Changi General Hospital (SG)
Publication Details
- Journal
- Singapore Medical Journal
- Published
- 2026-03-09
- DOI
- https://doi.org/10.4103/singaporemedj.smj-2025-138
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00