Key result
Deep learning retinal imaging predicts diabetic arterial stiffness with an AUC of ~0.78.
Why the study?
Pulse wave velocity is the gold standard for assessing arterial stiffness, but it is costly and not widely accessible.
Does a deep learning model applied to retinal fundus images accurately predict arterial stiffness compared to classical risk factors alone in adults with diabetes?
Observational (n=36,412)
Yes
Does a deep learning model applied to retinal fundus images accurately predict arterial stiffness compared to classical risk factors alone in adults with diabetes?
Answers are grounded in this paper and cite their sources.
Deep learning analysis of retinal fundus images, particularly when combined with clinical factors, provides a non-invasive and accessible screening tool for arterial stiffness in patients with diabetes.
Pulse wave velocity is the gold standard for assessing arterial stiffness (AS) but is costly and not widely accessible. This multicenter study developed a deep learning model to predict AS from fundus images. Trained on 64,440 images from 36,412 adults with diabetes at China's National Metabolic Management Centers and externally validated on 6,217 images from two independent hospitals, the model achieved an AUC of 0.780 (95% CI: 0.769–0.792) and 0.772 (95% CI: 0.754–0.790) in internal and external validation, respectively, outperforming models using classical risk factors alone. The fusion model integrating fundus images with clinical factors significantly improved test-set performance (AUC = 0.853, 95% CI: 0.844–0.863) and demonstrated good external generalizability (AUC = 0.801, 95% CI: 0.784–0.816). Ablation studies indicated retinal arteries were associated with AS, with other retinal structures also contributing. These findings support deep-learning-based fundus-image analysis for AS screening in real-world clinical settings, and retinal-structure analyses for exploring AS pathophysiology.
No takes yet. Share an insight, caveat, or question.
Zhao et al. (2026) conducted an observational in Diabetes and arterial stiffness (n=36,412). Deep learning model analysing retinal fundus images vs. Models using classical clinical risk factors alone was evaluated on Prediction of arterial stiffness (assessed by pulse wave velocity) (AUC 0.780 (internal), AUC 0.772 (external); Fusion model AUC 0.853 (internal), AUC 0.801 (external), 95% CI 0.769-0.792). Deep learning analysis of retinal fundus images predicted arterial stiffness in adults with diabetes with an AUC of 0.780 (95% CI 0.769–0.792), improving to 0.853 when fused with clinical factors.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: