Association Between Deep Learning Derived Retinal Aging Speed and eGFR slope in Japanese Health Checkup Participants

Certificate Output Instructions

For best output, select "Paper Size" as "A4" and "Margin" as "0" or "None".

To save or print to PDF, please select Print Destination > Save as PDF, enable Background Graphics under "More Settings", then click "Save".

Presented the abstract " "
(Abstract co-author(s): )

Back

E-Poster Presentation

During the congress, E-Posters will be accessible to all participants on the congress website 24/7, as well as in the E-poster stations in the congress center.

Preparing your E-Poster

Please review the E-Poster format requirements carefully when preparing your E-Poster. Should your E-Poster not meet the mentioned requirements, it may not be displayed as described above.

E-Poster Submission Deadline

Please prepare and upload your E-Poster no later than March 14, 2026 11.59PM CET. After this date, you will no longer be able to prepare and upload your E-poster and it will not be displayed and accessible on the congress website.

E-Poster Format Requirements

PDF file
Layout: Portrait (vertical orientation)
One page only (Dim A4: 210 x 297mm or PPT)
E-Poster can be prepared in PowerPoint (one (1) PowerPoint slide) but must be saved and submitted as PDF file.
File Size: Maximum file size is 2 Megabytes (2 MB)
No hyperlinks, animated images, animations, and slide transitions
Language: English
Include your abstract number
E-posters can include QR codes, tables and photos

E-Poster

https://storage.unitedwebnetwork.com/files/1099/7a429e03961d0d2b9af587cde8f2f869.pdf

Abstract Title *

Association Between Deep Learning Derived Retinal Aging Speed and eGFR slope in Japanese Health Checkup Participants

Please follow the instructions below to input your abstract title.

Abstract titles should be brief and reflect the content of the abstract.

The title will not be accepted if it exceeds 25 words.
Type in CAPITAL LETTERS.
Lowercase may be used for abbreviations only, for example, mRNA.

Co-author 1

Yoichi Kadoh ykadoh@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan *

Co-author 2

Jun Yoshino jyoshino@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 3

Tomohiro Oka t-oka@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 4

Fumika Kamei kameif@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 5

Ai Uchida a.uchida@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 6

Maki Hanada makkoi@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 7

Makoto Koyama minamikoyasuganka@gmail.com Minamikoyasu Eye Clinic Opthalmology Kimitsu Japan -

Co-author 8

Ryo Asaoka ryoasa0120@googlemail.com Seirei Hamamatsu General Hospital Opthalmology Hamamatsu Japan -

Co-author 9

Shigeki Muto smuto@sis.seirei.or.jp Seirei Hamamatsu General Hospital Opthalmology Hamamatsu Japan -

Co-author 10

Masaki Tanito mtanito@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 11

Takeshi Kanda t-kanda@med.shimane-u.ac.jp Shimane University Hospital Nephrology Izumo Japan -

Co-author 12

Co-author 13

Co-author 14

Co-author 15

Introduction

The eye and kidney share similar microvascular characteristics, and ocular aging may reflect systemic vascular and metabolic stress. Retinal microvasculature, which can be visualized noninvasively via fundus photography, provides a means of assessing systemic microvascular aging. Artificial intelligence (AI) based estimation of "retinal age" offers a novel indicator of biological aging. It remains unclear whether the rate of retinal aging “retinal aging speed” is associated with eGFR slope, which a robust predictor of cardiorenal prognosis.

Methods

We conducted a retrospective cohort study involving 10,454 Japanese health checkup participants (6,893 man and 3,561 women) from Seirei Hamamatsu General Hospital. The mean baseline age was 52.7 ± 9.6 years, with a mean follow-up period of 7.8 ± 0.46 years. Retinal age was estimated from fundus photographs using a validated deep-learning AI model. Retinal aging speed (years/year) was calculated by regressing estimated retinal age against examination time after adjusted for chronological age. eGFR was calculated by the Japanese equation, and eGFR slope (mL/min/1.73 m²/year) was determined by linear regression. Associations between retinal aging speed and eGFR slope were evaluated using a generalized linear mixed-effects model incorporating random effects for both eyes. Sensitivity analyses were performed with additional adjustment for relevant covariates.

Results

In the unadjusted model, a faster retinal aging speed was significantly associated with a steeper decline in eGFR slope (β = −0.024, p = 0.0139). This negative association remained significant after adjustment for confounding factors including sex, BMI, systolic blood pressure, HbA1c, and IOP, indicating that retinal aging speed independently correlates with renal function decline.

Conclusion

This study demonstrates that retinal aging speed, derived from AI-based retinal age estimation, is significantly associated with longitudinal eGFR decline. These findings support the concept that the retinal aging reflects systemic microvascular and metabolic aging processes.

Kewords