@article{zhou2026generalisability,
  title={Generalisability and Fairness of Retinal Age Prediction Models Across Diverse Populations},
  author={Zhou, Yukun and Ninomiya, Takahiro and Jonas, Rahul Arvo and Hou, Benjamin and Keenan, Tiarnan D. L. and Lu, Zhiyong and Hu, Wenyi and Zhu, Zhuoting and Liu, Xujia and Cheung, Carol Y. and Keane, Pearse Andrew and Wagner, Siegfried Karl},
  journal={Investigative Ophthalmology \& Visual Science},
  volume={67},
  number={7},
  pages={837--837},
  year={2026},
  publisher={The Association for Research in Vision and Ophthalmology},
  url={https://iovs.arvojournals.org/article.aspx?articleid=2813038},
  abstract={Retinal age, an imaging biomarker derived from fundus photographs, is a promising indicator of biological ageing and systemic health risk. However, how reliably and fairly retinal age models generalise across populations with differing demographics and imaging devices remains unclear. This study evaluates internal performance, age-related fairness, and external generalisability of retinal age prediction models developed in diverse real-world cohorts. Six retinal age models were independently trained using large datasets from the UK, China, Japan, Australia, USA, and Russia. Internal performance was assessed using mean absolute error and mean error with bootstrapped 95\% confidence intervals, and external generalisability was evaluated on three heterogeneous datasets. Retinal age models exhibited population-specific behaviour, age-dependent bias, and substantial loss of accuracy when applied outside their development cohorts, highlighting the need for diverse training data, modelling strategies that reduce systematic prediction drift, and fairness-aware evaluation frameworks.}
}