Is cardiovascular risk profiling from UK Biobank retinal images using explicit deep learning estimates of traditional risk factors equivalent to actual risk measurements? A prospective cohort study design
Our algorithm estimates the 5-year risk of MACE based on retinal images, while explicitly presenting which risk factors should be checked and intervened. This two-stage approach provides human interpretable information between stages, which helps clinicians gain insights into the screening process copiloting with the DL model.
Authors
- Ryo Kawasaki (ORCID: https://orcid.org/0000-0002-7492-6303)
- Yiming Qian (ORCID: https://orcid.org/0000-0002-1795-2038)
- Yuta Nakashima (ORCID: https://orcid.org/0000-0001-8000-3567)
- Hajime Nagahara (ORCID: https://orcid.org/0000-0003-1579-8767)
- Liangzhi Li (ORCID: https://orcid.org/0000-0002-8879-5957)
- Kohji Nishida (ORCID: https://orcid.org/0000-0001-8838-7593)
Institutions
- Osaka University Hospital (JP)
- The University of Osaka (JP)
Publication Details
- Journal
- BMJ Open
- Published
- 2024-10-01
- DOI
- https://doi.org/10.1136/bmjopen-2023-078609
- Citations
- 5
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 2.02
Funders
- National Institute of Biomedical Innovation
- Council for Science, Technology and Innovation
- Japan Society for the Promotion of Science