Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach
The MMDL model integrating retinal images and urine dipstick data show significant promise for noninvasive CKD screening, outperforming the retinal image-only model. However, routine blood tests are still recommended for individuals aged 65 years and older due to the model's limited performance in this age group.
Authors
- S.-H. Park
- Sang Min Nam (ORCID: https://orcid.org/0000-0001-6903-6333)
- Eun Seok Kang (ORCID: https://orcid.org/0000-0002-0364-4675)
- Hyun Wook Han (ORCID: https://orcid.org/0000-0002-6918-5694)
- Eun Chan Jang
- J. Kim (ORCID: https://orcid.org/0000-0002-3717-2223)
- Daehwan Lee (ORCID: https://orcid.org/0009-0003-8129-4548)
- Yu Ho Lee (ORCID: https://orcid.org/0000-0001-5231-0551)
- Kiwon Lee (ORCID: https://orcid.org/0000-0003-2658-4342)
- Christopher Seungkyu Lee (ORCID: https://orcid.org/0000-0001-5054-9470)
- Eunjeong Jang (ORCID: https://orcid.org/0000-0003-4267-5586)
- Youngmin Bhak (ORCID: https://orcid.org/0009-0002-7466-8786)
Institutions
- Yonsei University (KR)
- Severance Hospital (KR)
- CHA University Bundang Medical Center (KR)
- CHA University (KR)
- Ulsan National Institute of Science and Technology (KR)
- Chung-Ang University (KR)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-02-07
- DOI
- https://doi.org/10.2196/55825
- Citations
- 4
- Primary Topic
- Retinal Imaging and Analysis
- Type
- article
- Field-Weighted Citation Impact
- 5.44