Artificial Intelligence-enabled Retinal Vasculometry for Prediction of Circulatory Mortality, Myocardial Infarction and Stroke

Overview

Journal Br J Ophthalmol

Specialty Ophthalmology

Date 2022 Oct 4

PMID 36195457

Authors

Alicja Regina Rudnicka

Roshan Welikala

Sarah Barman

Paul J Foster

Robert Luben

Shabina Hayat

Kay-Tee Khaw

Peter Whincup

David Strachan

Christopher G Owen

Affiliations

Soon will be listed here.

Abstract

Aims: We examine whether inclusion of artificial intelligence (AI)-enabled retinal vasculometry (RV) improves existing risk algorithms for incident stroke, myocardial infarction (MI) and circulatory mortality.

Methods: AI-enabled retinal vessel image analysis processed images from 88 052 UK Biobank (UKB) participants (aged 40-69 years at image capture) and 7411 European Prospective Investigation into Cancer (EPIC)-Norfolk participants (aged 48-92). Retinal arteriolar and venular width, tortuosity and area were extracted. Prediction models were developed in UKB using multivariable Cox proportional hazards regression for circulatory mortality, incident stroke and MI, and externally validated in EPIC-Norfolk. Model performance was assessed using optimism adjusted calibration, C-statistics and R statistics. Performance of Framingham risk scores (FRS) for incident stroke and incident MI, with addition of RV to FRS, were compared with a simpler model based on RV, age, smoking status and medical history (antihypertensive/cholesterol lowering medication, diabetes, prevalent stroke/MI).

Results: UKB prognostic models were developed on 65 144 participants (mean age 56.8; median follow-up 7.7 years) and validated in 5862 EPIC-Norfolk participants (67.6, 9.1 years, respectively). Prediction models for circulatory mortality in men and women had optimism adjusted C-statistics and R statistics between 0.75-0.77 and 0.33-0.44, respectively. For incident stroke and MI, addition of RV to FRS did not improve model performance in either cohort. However, the simpler RV model performed equally or better than FRS.

Conclusion: RV offers an alternative predictive biomarker to traditional risk-scores for vascular health, without the need for blood sampling or blood pressure measurement. Further work is needed to examine RV in population screening to triage individuals at high-risk.

Citing Articles

Use of artificial intelligence with retinal imaging in screening for diabetes-associated complications: systematic review.

Yang Q, Bee Y, Lim C, Sabanayagam C, Yim-Lui Cheung C, Wong T EClinicalMedicine. 2025; 81:103089.

PMID: 40052065 PMC: 11883405. DOI: 10.1016/j.eclinm.2025.103089.

Artificial intelligence in stroke risk assessment and management via retinal imaging.

Khalafi P, Morsali S, Hamidi S, Ashayeri H, Sobhi N, Pedrammehr S Front Comput Neurosci. 2025; 19:1490603.

PMID: 40034651 PMC: 11872910. DOI: 10.3389/fncom.2025.1490603.

Retinal vasculometry associations with cognition status in UK Biobank.

Shakespeare R, Rudnicka A, Welikala R, Barman S, Khawaja A, Foster P Alzheimers Dement (Amst). 2025; 17(1):e270087.

PMID: 39996031 PMC: 11848343. DOI: 10.1002/dad2.70087.

Application of Artificial Intelligence in Acute Ischemic Stroke: A Scoping Review.

Heo J Neurointervention. 2025; 20(1):4-14.

PMID: 39961634 PMC: 11900286. DOI: 10.5469/neuroint.2025.00052.

Coronary artery and retinal vascularization by optical coherence tomography angiography: are eyes the window to the heart?.

Sakuno G, Sarraf D, Sadda S, Preti R, Oliveira B, Damico F Graefes Arch Clin Exp Ophthalmol. 2025; .

PMID: 39954049 DOI: 10.1007/s00417-025-06769-x.

References

Seidelmann S, Claggett B, Bravo P, Gupta A, Farhad H, Klein B . Retinal Vessel Calibers in Predicting Long-Term Cardiovascular Outcomes: The Atherosclerosis Risk in Communities Study. Circulation. 2016; 134(18):1328-1338. PMC: 5219936. DOI: 10.1161/CIRCULATIONAHA.116.023425. View

Ong Y, De Silva D, Cheung C, Chang H, Chen C, Wong M . Microvascular structure and network in the retina of patients with ischemic stroke. Stroke. 2013; 44(8):2121-7. DOI: 10.1161/STROKEAHA.113.001741. View

Chua S, Thomas D, Allen N, Lotery A, Desai P, Patel P . Cohort profile: design and methods in the eye and vision consortium of UK Biobank. BMJ Open. 2019; 9(2):e025077. PMC: 6398663. DOI: 10.1136/bmjopen-2018-025077. View

Hayat S, Luben R, Keevil V, Moore S, Dalzell N, Bhaniani A . Cohort profile: A prospective cohort study of objective physical and cognitive capability and visual health in an ageing population of men and women in Norfolk (EPIC-Norfolk 3). Int J Epidemiol. 2013; 43(4):1063-72. PMC: 4121549. DOI: 10.1093/ije/dyt086. View

Owen C, Rudnicka A, Welikala R, Fraz M, Barman S, Luben R . Retinal Vasculometry Associations with Cardiometabolic Risk Factors in the European Prospective Investigation of Cancer-Norfolk Study. Ophthalmology. 2018; 126(1):96-106. PMC: 6302796. DOI: 10.1016/j.ophtha.2018.07.022. View

Cheung C, Xu D, Cheng C, Sabanayagam C, Tham Y, Yu M . A deep-learning system for the assessment of cardiovascular disease risk via the measurement of retinal-vessel calibre. Nat Biomed Eng. 2020; 5(6):498-508. DOI: 10.1038/s41551-020-00626-4. View

Garcia M, Mulvagh S, Merz C, Buring J, Manson J . Cardiovascular Disease in Women: Clinical Perspectives. Circ Res. 2016; 118(8):1273-93. PMC: 4834856. DOI: 10.1161/CIRCRESAHA.116.307547. View

Welikala R, Foster P, Whincup P, Rudnicka A, Owen C, Strachan D . Automated arteriole and venule classification using deep learning for retinal images from the UK Biobank cohort. Comput Biol Med. 2017; 90:23-32. DOI: 10.1016/j.compbiomed.2017.09.005. View

Wang J, Liew G, Klein R, Rochtchina E, Knudtson M, Klein B . Retinal vessel diameter and cardiovascular mortality: pooled data analysis from two older populations. Eur Heart J. 2007; 28(16):1984-92. DOI: 10.1093/eurheartj/ehm221. View

10.

Sudlow C, Gallacher J, Allen N, Beral V, Burton P, Danesh J . UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age. PLoS Med. 2015; 12(3):e1001779. PMC: 4380465. DOI: 10.1371/journal.pmed.1001779. View

11.

Wong T, Klein R, Sharrett A, Duncan B, Couper D, Tielsch J . Retinal arteriolar narrowing and risk of coronary heart disease in men and women. The Atherosclerosis Risk in Communities Study. JAMA. 2002; 287(9):1153-9. DOI: 10.1001/jama.287.9.1153. View

12.

Steyerberg E, Vickers A, Cook N, Gerds T, Gonen M, Obuchowski N . Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2009; 21(1):128-38. PMC: 3575184. DOI: 10.1097/EDE.0b013e3181c30fb2. View

13.

Kaptoge S, Di Angelantonio E, Pennells L, Wood A, White I, Gao P . C-reactive protein, fibrinogen, and cardiovascular disease prediction. N Engl J Med. 2012; 367(14):1310-20. PMC: 3714101. DOI: 10.1056/NEJMoa1107477. View

14.

Tapp R, Owen C, Barman S, Welikala R, Foster P, Whincup P . Associations of Retinal Microvascular Diameters and Tortuosity With Blood Pressure and Arterial Stiffness: United Kingdom Biobank. Hypertension. 2019; 74(6):1383-1390. PMC: 7069386. DOI: 10.1161/HYPERTENSIONAHA.119.13752. View

15.

Wilson P, DAgostino R, Levy D, Belanger A, Silbershatz H, Kannel W . Prediction of coronary heart disease using risk factor categories. Circulation. 1998; 97(18):1837-47. DOI: 10.1161/01.cir.97.18.1837. View

16.

. Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet. 2018; 392(10159):1736-1788. PMC: 6227606. DOI: 10.1016/S0140-6736(18)32203-7. View

17.

McGeechan K, Liew G, Macaskill P, Irwig L, Klein R, Sharrett A . Risk prediction of coronary heart disease based on retinal vascular caliber (from the Atherosclerosis Risk In Communities [ARIC] Study). Am J Cardiol. 2008; 102(1):58-63. PMC: 2491714. DOI: 10.1016/j.amjcard.2008.02.094. View

18.

Pepine C, Kerensky R, Lambert C, Smith K, von Mering G, Sopko G . Some thoughts on the vasculopathy of women with ischemic heart disease. J Am Coll Cardiol. 2006; 47(3 Suppl):S30-5. DOI: 10.1016/j.jacc.2005.09.023. View

19.

Li L, Ikram M, Wong T . Retinal vascular imaging in early life: insights into processes and risk of cardiovascular disease. J Physiol. 2015; 594(8):2175-203. PMC: 4933111. DOI: 10.1113/JP270947. View

20.

Wang S, Mitchell P, Liew G, Wong T, Phan K, Thiagalingam A . A spectrum of retinal vasculature measures and coronary artery disease. Atherosclerosis. 2017; 268:215-224. DOI: 10.1016/j.atherosclerosis.2017.10.008. View