Prediction of Alzheimer's Disease Risk Factors from Retinal Images via Deep Learning: Development and Validation of Biologically Relevant Morphological Associations in the UK Biobank
Seowung Leem, Yunchao Yang, Adam J. Woods, Ruogu Fang
TLDR
Deep learning predicts 12 Alzheimer's risk factors from retinal images, identifying structural changes in the optic nerve and vasculature linked to AD vulnerability.
Key contributions
- DL models predict 12 AD-related risk factors (e.g., age, BMI, smoking) from retinal images with high accuracy.
- Saliency maps highlight optic nerve head and retinal vasculature as key regions for these predictions.
- Saliency scores differentiate incident AD cases from controls, suggesting preclinical AD changes.
- Retinal images encode signatures of AD risk factors, potentially reflecting AD vulnerability pathways.
Why it matters
This research demonstrates that deep learning can extract AD risk factor signatures from retinal images. It suggests that changes in the eye may reflect early AD vulnerability, offering a non-invasive approach for risk assessment and earlier identification.
Original Abstract
The systemic, metabolic, lifestyle factors have established associations with Alzheimer's Disease (AD) through epidemiologic and AD-specific biomarker studies. Whether colored fundus photography (CFP) contains retinal structural signatures corresponding to these AD-related risk domains remains unclear. To determine whether deep learning (DL) models can predict 12 AD-related risk factors from CFP and to characterize the retinal structures underlying these predictions, thereby assessing whether CFP reflects pathways to AD vulnerability. Using UK Biobank CFPs, DL models were trained using 62,876 images from 44,501 unique participants to predict 12 factors linked to AD incidence: 6 categorical (sex, smoking, sleeplessness, economic status, alcohol use, depression) and 6 continuous (age, age at completing education, BMI, systolic, diastolic blood pressure, HbA1c). Model performance, model saliency, and saliency-derived scores (CAM-Score) were evaluated and compared to retinal morphometry. The scores were also compared between incident-AD cases (average 8.55 years before onset) and matched controls. Performance of DL ranged from AUROC= 0.5654-0.9480 for categorical and R2=-0.0291-0.7620 for continuous factors, outperforming most of the morphometry-machine learning models. Saliency-based score consistently highlighted biologically meaningful regions, particularly the optic nerve head and retinal vasculature. It also aligned with present morphometric variations. Several saliency-based scores differed significantly between incident AD and matched controls, suggesting potential overlap between retinal correlates of risk factors and preclinical AD-associated changes. CFP encodes retinal signatures linked to AD risk factors. Although not diagnostic, DL-derived retinal representations may uncover biologically meaningful risk-related structural changes mirroring the potential AD vulnerability.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.