EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Association between deep-learning-derived retinal aging speed and rapid decline of renal function in the Japanese general population

Yoichi Kadoh, Jun Yoshino iD, Makoto Koyama, Ryo Asaoka, Shigeki Muto, Tomohiro Oka, Misaki Nakamura, Fumika Kamei, Ai Uchida, Maki Hanada, Toshihiko Kawamura, Kazunobu Sugihara und 2 weitere

Clinical Kidney Journal · 02.11.2026 · 19 (11)

DOI: 10.1093/ckj/sfag391 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Clinical Kidney Journal, online erschienen am 06.11.2026. Verfasst von Yoichi Kadoh und 13 weiteren Autor:innen. Beteiligte Einrichtung: Division of Nephrology, Department of Internal Medicine, Faculty of Medicine, Shimane University, Izumo, Japan. Die Arbeit nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

The eye and the kidney share microvascular features, and retinal changes have been postulated to reflect systemic cardiometabolic dysfunction. Recently, retinal age, estimated by deep learning (DL) from a single fundus photograph, has been shown to predict cardiovascular events. The present study aimed to determine whether retinal aging speed, defined as the individual-specific annual rate of change in DL-estimated retinal age, is associated with rapid estimated glomerular filtration rate (eGFR) decline.

Methods

We retrospectively analyzed the longitudinal data obtained from 7807 Japanese individuals who underwent repeated health check-ups with serial measurements of eGFR and fundus photographs (median 9.0 visits over median 8.0 years). We evaluated the relationship between retinal aging speed during the baseline period (from baseline to year 4) and rapid eGFR decline (≤ −3 ml/min/1.73 m²/year) during the follow-up period (after year 4).

Results

The incidence of rapid eGFR decline was significantly higher in the highest quartile of retinal aging speed than in the lowest quartile as the reference group in the fully adjusted model adjusting age, sex, body mass index, blood pressure, diabetes, smoking, eGFR, and proteinuria [odds ratio (OR) 1.34; 95% confidence interval (CI) 1.06–1.68; P = .015]. In the multivariable logistic regression models, retinal aging speed was associated with rapid eGFR decline after adjusting multiple key confounders (OR 1.14; 95% CI 1.02–1.29; P = .027).

Conclusions

Taken together, DL-derived retinal aging speed is independently associated with rapid eGFR decline in the Japanese general population.

Schlagwörter

Stichwörter der Autor:innen

artificial intelligencechronic kidney diseasedeep learningrapid eGFR declineretinal aging speed

Autor:innen und Institutionen

  • Division of Nephrology, Department of Internal Medicine, Faculty of Medicine, Shimane University, Izumo, Japan.
  • The Center for Integrated Kidney Research and Advance (IKRA), Faculty of Medicine, Shimane University, Izumo, Japan.
  • Minamikoyasu Eye Clinic, Kimitsu, Japan.
  • Department of Ophthalmology, Seirei Hamamatsu General Hospital, Hamamatsu, Japan.
  • Seirei Center for Health Promotion and Preventive Medicine, Hamamatsu, Japan.
  • Department of Medical Informatics, Faculty of Medicine, Shimane University, Izumo, Japan.

ORCID-Profile: Jun Yoshino, Takeshi Kanda

Zitieren

APA

Kadoh, Y., Yoshino, J., Koyama, M., Asaoka, R., Muto, S., Oka, T., Nakamura, M., Kamei, F., Uchida, A., Hanada, M., Kawamura, T., Sugihara, K., Tanito, M., & Kanda, T. (2026). Association between deep-learning-derived retinal aging speed and rapid decline of renal function in the Japanese general population. Clinical Kidney Journal, 19(11). https://doi.org/10.1093/ckj/sfag391

Vancouver

Kadoh Y, Yoshino J, Koyama M, Asaoka R, Muto S, Oka T, et al. Association between deep-learning-derived retinal aging speed and rapid decline of renal function in the Japanese general population. Clinical Kidney Journal. 2026;19(11). doi:10.1093/ckj/sfag391

BibTeX
@article{Kadoh2026,
  author = {Kadoh, Yoichi and Yoshino, Jun and Koyama, Makoto and Asaoka, Ryo and Muto, Shigeki and Oka, Tomohiro and Nakamura, Misaki and Kamei, Fumika and Uchida, Ai and Hanada, Maki and Kawamura, Toshihiko and Sugihara, Kazunobu and Tanito, Masaki and Kanda, Takeshi},
  title = {Association between deep-learning-derived retinal aging speed and rapid decline of renal function in the Japanese general population},
  journal = {Clinical Kidney Journal},
  year = {2026},
  volume = {19},
  number = {11},
  doi = {10.1093/ckj/sfag391}
}
Kostenlos starten →