Overview of examine design (created with biorender.com). Credit score: Alzheimer’s & Dementia (2025). DOI: 10.1002/alz.14601
A brand new examine led by researchers from the Yong Lavatory Lin College of Medication on the Nationwide College of Singapore (NUS Medication) has demonstrated that synthetic intelligence (AI) evaluation of retinal images can predict a person’s threat of cognitive decline and dementia. Revealed in Alzheimer’s & Dementia, this first-of-its-kind examine in Singapore highlights the potential of retinal getting old biomarkers as a novel device for mind well being administration.
Collectively led by Professor Cheng Ching-Yu, director, Heart for Innovation and Precision Eye Well being, NUS Medication, and Professor Christopher Chen, deputy chair, Wholesome Longevity Translational Analysis Programme, NUS Medication, the analysis workforce developed a novel deep-learning biomarker generally known as RetiPhenoAge, which estimates the organic age of the retina primarily based on customary eye pictures.
The examine analyzed knowledge from over 500 members recruited from reminiscence clinics in Singapore. The findings confirmed that people with greater retinal organic age had been at considerably higher threat (as much as 25–40% elevated threat, per customary deviation enhance in RetiPhenoAge) of creating cognitive decline or dementia over a five-year interval.
These findings had been additional validated in a bigger inhabitants pattern utilizing knowledge from greater than 33,000 members within the UK Biobank. On this cohort, elevated RetiPhenoAge was equally related to a better threat of creating dementia over twelve years of follow-up, reinforcing its predictive utility throughout numerous populations.
The examine additional confirmed that retinal getting old displays key organic processes related to neurodegeneration, with mind scans and blood markers used to validate RetiPhenoAge’s hyperlink to mind modifications and aging-related modifications in blood proteins. These associations provide a novel various for the usage of retinal getting old as a proxy measure for cognitive well being.
Prof Cheng stated, “With RetiPhenoAge, we are able to non-invasively estimate an individual’s biological age, offering valuable insights for both cognitive health management and broader aging research. This can help doctors identify people at risk of cognitive decline or dementia, before symptoms appear, enabling more targeted interventions. We hope to validate this screening tool in larger and more diverse populations, and assess its impact in clinical settings to guide earlier treatment of dementia.”
Prof Chen added, “With dementia numbers rising globally, we urgently need tools that are both scalable and predictive. RetiPhenoAge could hold the key to community-level screening that is both effective and affordable. These findings bring us closer to developing simple and affordable screening modalities that can be integrated into routine health checks, enabling earlier detection of dementia risk and timely support.”
Prof Chen can also be from the Division of Pharmacology at NUS Medication, and is the director of the Reminiscence, Getting older and Cognition Centre, NUHS and visiting guide, Division of Psychological Medication, Nationwide College Hospital (NUH).
Co-first authors of the examine, Dr. Sim Ming Ann and Asst Prof Tham Yih Chung, added, “We hope that these findings will lead to improvements in care, which will help doctors identify people at risk of dementia before symptoms appear, which may lead to earlier interventions and improved patient outcomes.”
Dr. Sim is a guide on the Ng Teng Fong Basic Hospital and NUH, and a Ph.D. candidate at NUS Medication, whereas Asst Prof Tham is from the Heart for Innovation and Precision Eye Well being, NUS Medication.
This examine marks a big development within the subject of digital biomarkers and demonstrates the potential of mixing AI with non-invasive imaging to sort out urgent well being care challenges. As RetiPhenoAge makes use of retinal scans from current imaging instruments already obtainable in lots of Singapore polyclinics, it presents a handy and scalable resolution that may be seamlessly built-in into routine well being checks. The analysis workforce is presently working to validate the biomarker throughout numerous populations in Asia and past, in addition to to evaluate its applicability in each scientific and group well being care settings.
Constructing upon this work, Prof Cheng and Prof Chen will use retinal imaging to display screen individuals with cognitive impairment in the neighborhood. They’re additionally exploring how RetiPhenoAge is likely to be used to trace particular person responses to interventions geared toward slowing or stopping cognitive decline and dementia, akin to way of life modifications, pharmacological therapies, and different therapeutic approaches.
Extra info:
Ming Ann Sim et al, A deep‐studying retinal getting old biomarker for cognitive decline and incident dementia, Alzheimer’s & Dementia (2025). DOI: 10.1002/alz.14601
Supplied by
Nationwide College of Singapore
Quotation:
AI-powered eye scan predicts threat of cognitive decline and dementia (2025, September 11)
retrieved 11 September 2025
from https://medicalxpress.com/information/2025-09-ai-powered-eye-scan-cognitive.html
This doc is topic to copyright. Other than any honest dealing for the aim of personal examine or analysis, no
half could also be reproduced with out the written permission. The content material is offered for info functions solely.
