A deep learning model for detection of Alzheimer's disease based on retinal photographs: a retrospective, multicentre case-control study
importance 7/10
partially solved
Retinal Imaging and Analysis dementia screening stage: research
Problem
No simple screening model exists for Alzheimer's disease; diagnosis relies on expensive, sometimes invasive tests unavailable outside specialised settings.
Why it matters
Cheap, non-invasive screening could widen access to early Alzheimer's detection.
What the AI did
A deep learning algorithm was trained, validated, and tested on retinal photographs from 11 studies across countries to detect Alzheimer's disease-dementia.
Results
not stated in source
Impact
The study shows retinal photographs may support Alzheimer's screening, pending further validation.
Record
| Venue | The Lancet Digital Health |
|---|---|
| Published | 2022 |
| Work type | article |
| Authors | Carol Yim-lui Cheung, An Ran Ran, Shujun Wang, Victor T.T. Chan, Kaiser Sham, Saima Hilal, Narayanaswamy Venketasubramanian, Ching‐Yu Cheng et al. |
| Citations | 264 (OpenAlex, at import time) |
| References | 29 |
| Model or method | bilateral deep learning model |
| Organization | not stated in source |
| Primary source | https://doi.org/10.1016/s2589-7500(22)00169-8 |
| Open access | gold |
| Keywords | deep learning, Alzheimer's disease, retinal photographs, screening, dementia detection |
Importance rating
7
significant — thousands to millions affected
Cheap, non-invasive Alzheimer's screening could widen access beyond specialized settings; major disease but abstract gives no scale.