A deep learning system for retinal vessel calibre improves cardiovascular risk prediction in Asians with chronic kidney disease

Cynthia Ciwei Lim; Crystal Chong; Gavin Tan; Chieh Suai Tan; Carol Y Cheung; Tien Y Wong; Ching Yu Cheng; Charumathi Sabanayagam

doi:10.1093/ckj/sfad227

A deep learning system for retinal vessel calibre improves cardiovascular risk prediction in Asians with chronic kidney disease

Clin Kidney J. 2023 Sep 19;16(12):2693-2702. doi: 10.1093/ckj/sfad227. eCollection 2023 Dec.

Authors

Cynthia Ciwei Lim¹, Crystal Chong², Gavin Tan^{2

3}, Chieh Suai Tan¹, Carol Y Cheung⁴, Tien Y Wong¹, Ching Yu Cheng^{2

3}, Charumathi Sabanayagam^{2

3}

Affiliations

¹ Department of Renal Medicine, Singapore General Hospital, Singapore.
² Singapore Eye Research Institute, Singapore National Eye Center, Singapore.
³ Eye-ACP, Duke-NUS Medical School, Singapore.
⁴ Department of Ophthalmology and Visual Sciences, The Chinese University of Hong Kong, Hong Kong, China.

Abstract

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.

Keywords: artificial intelligence; cardiovascular disease; chronic kidney disease; microvascular disease; risk prediction.