Researchers at St George’s University of London used the QUARTZ (QUantitative Analysis of Retinal vessels Topology and siZe) retinal image analysis algorithm, developed in a previous study, and applied retinal vasculometry (RV) to it to predict cardiovascular disease, risk of myocardial infarction or stroke. The study titled “Artificial intelligence-enabled retinal vasculometry for prediction of circulatory mortality, myocardial infarction and stroke” was published online in early October in the British Journal of Ophthalmology.
Cardio-neurovascular diseases, a set of disorders affecting the heart and blood vessels, are the leading cause of death in the world. According to the French Federation of Cardiology, their number is increasing each year and they are responsible for around 140,000 deaths per year, or 400 deaths per day in France. They also lead to 40,000 cardiac arrests each year, 92% of which are fatal.
Using Retinal Scans to Predict Cardiovascular Events
A retinal scan, a very quick test, uses a low-intensity light source and sensor to scan the blood vessels at the back of the retina and is commonly performed by ophthalmologists. The biomarkers of these vessels (density, tortuosity, etc.) are associated with cardiac function and are increasingly used to predict cardiac problems, as researchers from KU Leuven have done or, long before them, those from Alphabet. .
However, according to the team from St George’s University of London, joined by researchers from Kingston University, the College of London and Cambridge, this research is the largest population-based study of RV and on the other hand, the external validation of the prediction models was carried out in a large separate cohort, which is rare in this field.
AI-based retinal vasculometry for the prediction of circulatory mortality, myocardial infarction and stroke
The objective of this study was to test whether the inclusion of Quartz AI-enabled VR improves existing risk algorithms for stroke, myocardial infarction (MI), and circulatory mortality.
Quartz-enabled retinal vessel image analysis processed images of 88,052 participants aged 40-69 from the UK Biobank (UKB), a large-scale biomedical database containing in-depth genetic and health information of half a million British participants. Retinal width, tortuosity, arteriolar and venular surface were extracted from these images to develop predictive models using multivariate Cox proportional hazards regression for circulatory mortality, stroke, and MI. Besides RV, the models took into account age, smoking, and medical history (antihypertensive/cholesterol-lowering drugs, diabetes, stroke prevalent).
They were then validated on the retinal scans of 7,411 people aged 48 to 92 who took part in the EPIC-Norfolk survey, the British component of the EPIC study (European Prospective Investigation into Cancer).
Researchers added VR to Framingham Risk Scores (FRS), which estimates coronary risk over a 10-year period, they found that FRS’s performance for stroke and MI did not differ. improved and that, on the other hand, those of Quartz were equal to or greater than those of the FRS.
AI-based vasculometry risk prediction is fully automated, inexpensive, non-invasive. It has the potential to reach a higher proportion of the population, however further work is needed to identify those at high risk of circulatory mortality.
Sources of the article:
“Artificial intelligence-based retinal vasculometry for the prediction of circulatory mortality, myocardial infarction and stroke”
British Journal of Ophthalmology, 04 October 2022, doi:10.1136/bjo-2022-321842
- Alicja Regina Rudnicka, Institute of Health Research, St George’s University London;
- Roshan Welikala, Faculty of Science, Engineering and Computing, Kingston University;
- Sarah Barman, Faculty of Science, Engineering and Computing, Kingston University;
- Paul J Foster, NIHR Biomedical Research Center at Moorfields Eye Hospital and UCL Institute of Ophthalmology, University College London;
- Robert Luben, University of Cambridge MRC Epidemiology Unit;
- Shabina Hayat 5, Department of Psychiatry, Cambridge Public Health, University of Cambridge School of Clinical Medicine;
- Kay-Tee Khaw, University of Cambridge MRC Epidemiology Unit;
- Pierre Whincup, Health Research Institute, St George’s University London;
- David Strachan, Institute of Health Research, St George’s University London;
- Christophe G Owen, Health Research Institute, St George’s University London.