Related Experiment Video
Updated: Jul 9, 2025
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
A deep learning system for retinal vessel calibre improves cardiovascular risk prediction in Asians with chronic
Cynthia Ciwei Lim1, Crystal Chong2, Gavin Tan2,3
1Department of Renal Medicine, Singapore General Hospital, Singapore.
Insights
Cardiovascular disease (CVD) risk in chronic kidney disease (CKD) patients can be improved by assessing retinal vessel calibre. Automated retinal imaging combined with kidney function data enhances CVD prediction in Asian populations.
Area of Science:
- Ophthalmology
- Nephrology
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Cardiovascular disease (CVD) and mortality rates are significantly higher in individuals with chronic kidney disease (CKD).
- Retinal vessel calibre, measurable from retinal photographs, is linked to cardiovascular risk.
- Automated retinal image analysis offers a potential tool for improving CVD risk prediction in CKD patients.
Purpose of the Study:
- To investigate the association between retinal vessel calibre, measured by a deep learning system (DLS), and incident CVD in a cohort of CKD patients.
- To determine if retinal vessel calibre measurements, alongside kidney function (eGFR), improve CVD risk prediction beyond established cardiovascular risk factors.
Main Methods:
- A retrospective cohort study of 860 participants with CKD (eGFR <60 ml/min/1.73 m²) from the Singapore Epidemiology of Eye Diseases Study.
- Retinal vessel calibre was measured using a DLS; incident CVD was ascertained over a mean follow-up of 9.3 years.
- Cox proportional hazards regression models were used to examine risk factors, with model performance assessed using discrimination, fit, and net reclassification improvement (NRI).
Main Results:
- Incident CVD occurred in 33.6% of participants.
- Retinal arteriolar narrowing (HR 1.40) and reduced eGFR (HR 0.98) were independent predictors of CVD in CKD patients, after adjusting for traditional risk factors.
- The addition of eGFR and retinal features significantly improved CVD risk prediction models (NRI 5.8% to 12.7%).
Conclusions:
- Automated retinal vessel calibre measurements are associated with incident CVD in CKD patients, independent of established risk factors.
- Incorporating kidney function and retinal vessel calibre parameters into risk prediction models enhances CVD risk assessment for Asian individuals with CKD.
Backgraund:
Cardiovascular disease (CVD) and mortality is elevated in chronic kidney disease (CKD). Retinal vessel calibre in retinal photographs is associated with cardiovascular risk and automated measurements may aid CVD risk prediction.
Methods:
Retrospective cohort study of 860 Chinese, Malay and Indian participants aged 40-80 years with CKD [estimated glomerular filtration rate (eGFR) <60 ml/min/1.73 m2] who attended the baseline visit (2004-2011) of the Singapore Epidemiology of Eye Diseases Study. Retinal vessel calibre measurements were obtained by a deep learning system (DLS). Incident CVD [non-fatal acute myocardial infarction (MI) and stroke, and death due to MI, stroke and other CVD] in those who were free of CVD at baseline was ascertained until 31 December 2019. Risk factors (established, kidney, and retinal features) were examined using Cox proportional hazards regression models. Model performance was assessed for discrimination, fit, and net reclassification improvement (NRI).
Results:
Incident CVD occurred in 289 (33.6%) over mean follow-up of 9.3 (4.3) years. After adjusting for established cardiovascular risk factors, eGFR [adjusted HR 0.98 (95% CI: 0.97-0.99)] and retinal arteriolar narrowing [adjusted HR 1.40 (95% CI: 1.17-1.68)], but not venular dilation, were independent predictors for CVD in CKD. The addition of eGFR and retinal features to established cardiovascular risk factors improved model discrimination with significantly better fit and better risk prediction according to the low (<15%), intermediate (15-29.9%), and high (30% or more) risk categories (NRI 5.8%), and with higher risk thresholds (NRI 12.7%).
Conclusions:
Retinal vessel calibre measurements by DLS were significantly associated with incident CVD independent of established CVD risk factors. Addition of kidney function and retinal vessel calibre parameters may improve CVD risk prediction among Asians with CKD.
