Estimating chronological age from flicker-induced retinal vascular reactivity: a machine learning approach

Abstract

This study proposes a novel, non-invasive approach to chronological age (CA) estimation by leveraging the Extra Trees Regressor to analyze retinal vessel reactivity to flicker light stimulation as a unique biomarker. By capturing and interpreting the dynamic responses of retinal blood vessels, we aim to develop an accessible and reliable tool for assessing chronological age, contributing to the emerging field of personalized anti-aging medicine through individualized insights into aging. Our method focuses on vascular function analysis using non-invasive dynamic vessel response measurements, offering a unique contribution compared to existing techniques. In this paper, multiple machine learning and deep learning models are employed to conduct experiments that estimate patient age using retinal arterial and venous vessel diameter changes across three flicker cycles. The best-performing model achieved a mean absolute error (MAE) of 9.3, a root mean squared error (RMSE) of 12.4, and a Mean Absolute Percentage Error (MAPE) value of 17.7%, demonstrating acceptable reliability and accuracy. Additionally, the application of Local Interpretable Model-agnostic Explanations (LIME) to our time series age estimation model provided valuable insights into the key features influencing predictions. To our knowledge, this is the first study to demonstrate that retinal vascular reactivity can serve as a functional biomarker for estimating chronological age, providing a foundation for future research on non-invasive markers of aging.

A chronological framework for atherosclerosis: from environmental pressure to clinical disease, with vascular aging as a cross-cutting dimension
Jorge E. Montoya-Pérez, Juan R. Serna-Garza, Abraham E. Gracia-Ramos
Frontiers in Cardiovascular Medicine7 Oct 2026Peer-reviewedCC BY 4.0Full textCardiovascular medicineCrossrefEurope PMC
Cannabigerol Modulates Blood Pressure and Vascular Reactivity in a Rat Model of Hypertension and Platelet Responses in Human Blood In Vitro
Anna Krzyżewska, Krzysztof Mińczuk, Tomasz Misztal +2
Molecules (Basel, Switzerland)1 Oct 2026Peer-reviewedCC BYFull textPharmacology & toxicologyEurope PMCCrossref
Agreement between upper-arm and wrist cuff occlusion for the assessment of vascular reactivity by digital thermal monitoring
Hamidreza Mohammadi, Ali Hashemi, Timothy O’Brien +4
Frontiers in Physiology12 Oct 2026Peer-reviewedCC BY 4.0Full textCardiovascular medicinePMCEurope PMC
Bayesian Anchored Latent Learning for Estimating State Trajectories
J. B. Gibbons, N. Leenaerts, A. D. Mandavia +11
medRxiv30 Sep 2026PreprintAll rights reservedFull textEpidemiology & public healthmedRxiv
Absolute and lung volume-normalized deep learning-derived pulmonary vascular measures in idiopathic pulmonary fibrosis: distinct clinical associations and the role of lung volume in prognosis
Gaetano Rea, Stefano Sanduzzi Zamparelli, Annalisa Mazzocca +4
Frontiers in medicine16 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeX RIS

BibTeX

@article{assaf2026estimating,
  title = {{Estimating chronological age from flicker-induced retinal vascular reactivity: a machine learning approach}},
  author = {Abdelrahman Assaf and Baha A. Alsaify and Omar Y. AlJarrah and Shen Li and Arno Schmidt-Trucksaess and Adnan Kilani and Konstantin Kotliar and Ines Lanzl},
  journal = {Scientific Reports},
  year = {2026},
  month = oct,
  doi = {10.1038/s41598-026-75953-8},
  url = {https://www.nature.com/articles/s41598-026-75953-8},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - Estimating chronological age from flicker-induced retinal vascular reactivity: a machine learning approach
AU  - Abdelrahman Assaf
AU  - Baha A. Alsaify
AU  - Omar Y. AlJarrah
AU  - Shen Li
AU  - Arno Schmidt-Trucksaess
AU  - Adnan Kilani
AU  - Konstantin Kotliar
AU  - Ines Lanzl
PY  - 2026
DA  - 2026/10/22
JO  - Scientific Reports
DO  - 10.1038/s41598-026-75953-8
UR  - https://www.nature.com/articles/s41598-026-75953-8
AB  - This study proposes a novel, non-invasive approach to chronological age (CA) estimation by leveraging the Extra Trees Regressor to analyze retinal vessel reactivity to flicker light stimulation as a unique biomarker. By capturing and interpreting the dynamic responses of retinal blood vessels, we aim to develop an accessible and reliable tool for assessing chronological age, contributing to the emerging field of personalized anti-aging medicine through individualized insights into aging. Our method focuses on vascular function analysis using non-invasive dynamic vessel response measurements, offering a unique contribution compared to existing techniques. In this paper, multiple machine learning and deep learning models are employed to conduct experiments that estimate patient age using retinal arterial and venous vessel diameter changes across three flicker cycles. The best-performing model achieved a mean absolute error (MAE) of 9.3, a root mean squared error (RMSE) of 12.4, and a Mean Absolute Percentage Error (MAPE) value of 17.7%, demonstrating acceptable reliability and accuracy. Additionally, the application of Local Interpretable Model-agnostic Explanations (LIME) to our time series age estimation model provided valuable insights into the key features influencing predictions. To our knowledge, this is the first study to demonstrate that retinal vascular reactivity can serve as a functional biomarker for estimating chronological age, providing a foundation for future research on non-invasive markers of aging.
SN  - 2045-2322
ER  -

Abstract

Related

Cite