WEDNESDAY, Oct. 5, 2022 (HealthDay News) -- Artificial intelligence (AI)-enabled retinal vasculometry (RV) can help predict circulatory mortality, incident stroke, and myocardial infarction (MI), according to a study published online Oct. 4 in the British Journal of Ophthalmology.
Alicja Regina Rudnicka, M.D., from St. George's University of London, and colleagues used images from 88,052 U.K. Biobank participants and 7,411 European Prospective Investigation into Cancer (EPIC)-Norfolk participants to examine whether inclusion of AI-enabled RV improves existing risk algorithms for incident stroke, MI, and circulatory mortality. Prognostic models were developed on 65,144 U.K. Biobank participants and validated in 5,862 EPIC-Norfolk participants.
The researchers found that the prediction models for circulatory mortality had optimism-adjusted C-statistics and R2 statistics between 0.75 to 0.77 and 0.33 to 0.44, respectively, in men and women. The addition of RV to Framingham risk scores did not improve model performance in either cohort for incident stroke and MI. The simpler RV model based on RV, age, smoking status, and medical history performed equally or better than the Framingham risk score.
"The results strengthen the evidence from several similar studies that the retina can be a useful and potentially disruptive source of information for cardiovascular disease risk in personalized medicine," write the authors of an accompanying editorial. "As the authors discuss, the accessibility of large repositories of retinal photography does make this concept particularly attractive as it enables validation of hypotheses in large, richly phenotyped cohorts."