EUVIMEDSkopri EUVIMED
Open access

Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach

Youngmin Bhak iD, Yu Ho Lee iD, Joonhyung Kim iD, Kiwon Lee iD, Daehwan Lee iD, Eun Chan Jang iD, Eunjeong Jang iD, Christopher Seungkyu Lee iD, Eun Seok Kang iD, Sehee Park iD, Hyun Wook Han iD, Sang Min Nam iD

JMIR Medical Informatics · 2025-02-07 · 13 · e55825-e55825

DOI: 10.2196/55825 ↗

At a glance

Journal article in JMIR Medical Informatics, published online on 2025-02-07. Written by Youngmin Bhak and 11 co-authors. Institution: Korean Genomics Center (KOGIC), Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea. Major MEDLINE topics: Deep Learning, Renal Insufficiency, Chronic, Retina, Urinalysis. Cited 15 times so far (Crossref); 52 references. The full text is freely available in PubMed Central.

AstrattSubjectsDettalji biblijografiċiCiteRelated studies

Abstract (original language)

Background

Chronic kidney disease (CKD) is a prevalent condition with significant global health implications. Early detection and management are critical to prevent disease progression and complications. Deep learning (DL) models using retinal images have emerged as potential noninvasive screening tools for CKD, though their performance may be limited, especially in identifying individuals with proteinuria and in specific subgroups.

Objective

We aim to evaluate the efficacy of integrating retinal images and urine dipstick data into DL models for enhanced CKD diagnosis.

Methods

The 3 models were developed and validated: eGFR-RIDL (estimated glomerular filtration rate–retinal image deep learning), eGFR-UDLR (logistic regression using urine dipstick data), and eGFR-MMDL (multimodal deep learning combining retinal images and urine dipstick data). All models were trained to predict an eGFR

Subjects

MeSH terms (MEDLINE)

Deep LearningRenal Insufficiency, ChronicRetinaUrinalysisHumansMiddle AgedMaleAgedFemaleAdultGlomerular Filtration RateYoung Adult

Author keywords

chronic kidney diseasefundus imagemultimodal deep learningsaliency mapurine dipstick

Authors and institutions

  • Korean Genomics Center (KOGIC), Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea.
  • Department of Biomedical Engineering, College of Information and Biotechnology, Ulsan National Institute of Science and Technology (UNIST), Ulsan, Republic of Korea.
  • Division of Nephrology, Department of Internal Medicine, CHA Bundang Medical Center, CHA University, Gyeonggi-do, Republic of Korea.
  • Department of Ophthalmology, CHA Bundang Medical Center, CHA University, Gyeonggi-do, Republic of Korea.
  • Spidercore Inc, Daejeon, Republic of Korea.
  • Department of Biomedical Informatics, School of Medicine, CHA University, 335 Pangyo-ro, Seongnam, Republic of Korea, 82 31-881-7964, 82 31-881-7069.

ORCID profiles: Youngmin Bhak, Yu Ho Lee, Joonhyung Kim, Kiwon Lee, Daehwan Lee, Eun Chan Jang, Eunjeong Jang, Christopher Seungkyu Lee, Eun Seok Kang, Sehee Park, Hyun Wook Han, Sang Min Nam

Cite

APA

Bhak, Y., Lee, Y. H., Kim, J., Lee, K., Lee, D., Jang, E. C., Jang, E., Lee, C. S., Kang, E. S., Park, S., Han, H. W., & Nam, S. M. (2025). Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach. JMIR Medical Informatics, 13, e55825-e55825. https://doi.org/10.2196/55825

Vancouver

Bhak Y, Lee YH, Kim J, Lee K, Lee D, Jang EC, et al. Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach. JMIR Medical Informatics. 2025;13:e55825-e55825. doi:10.2196/55825

BibTeX
@article{Bhak2025,
  author = {Bhak, Youngmin and Lee, Yu Ho and Kim, Joonhyung and Lee, Kiwon and Lee, Daehwan and Jang, Eun Chan and Jang, Eunjeong and Lee, Christopher Seungkyu and Kang, Eun Seok and Park, Sehee and Han, Hyun Wook and Nam, Sang Min},
  title = {Diagnosis of Chronic Kidney Disease Using Retinal Imaging and Urine Dipstick Data: Multimodal Deep Learning Approach},
  journal = {JMIR Medical Informatics},
  year = {2025},
  volume = {13},
  pages = {e55825--e55825},
  doi = {10.2196/55825}
}
Start for free →