ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ В ОЦЕНКЕ СОСУДИСТЫХ ИЗМЕНЕНИЙ НА ГЛАЗНОМ ДНЕ: ВОЗМОЖНОСТИ РАННЕЙ ДИАГНОСТИКИ СЕРДЕЧНО-СОСУДИСТОГО РИСКА
Open Access
- 6 November 2025
- journal article
- Published by Scientific Innovations in Advanced Ophthalmology
- Vol. 14 (3) , 32-38
Abstract
Relevance. Early detection of cardiovascular risk remains a key objective of preventive medicine. The development of artificial intelligence (AI) technologies offers new opportunities for the quantitative analysis of retinal vessels in a screening context. Purpose of the study. To assess the prevalence and clinical significance of retinal vascular changes identified using AI in individuals aged 35-50 years with cardiovascular risk factors. Materials and methods. A total of 120 individuals (58 men and 62 women) without manifest cardiovascular disease were examined. All participants underwent fundus photography followed by image analysis using the RMHAS platform. The following parameters were evaluated: CRAE (Central Retinal Arteriolar Equivalent - average diameter of retinal arterioles); CRVE (Central Retinal Venular Equivalent - average diameter of retinal venules); AVR (Arteriovenous Ratio); vessel tortuosity index; fractal dimension; vessel density; and vascular asymmetry. Results and conclusion. The most common findings were venular dilation (34,2%), arteriolar narrowing (28,3%), and AVR<0,66 (12,5%). AVR showed a strong negative correlation with systolic blood pressure (r= -0,45), while CRVE was positively correlated with HbA1c (r=0,31). A combined analysis of parameters yielded an AUC of 0,82 for predicting multiple risk factors. AI-based retinal vessel analysis is a non-invasive and sensitive method for early detection of cardiovascular risk in the general population, demonstrating high prognostic potential.Keywords
This publication has 8 references indexed in Scilit:
- Is cardiovascular risk profiling from UK Biobank retinal images using explicit deep learning estimates of traditional risk factors equivalent to actual risk measurements? A prospective cohort study designBMJ Open, 2024
- Prediction of cardiovascular risk factors from retinal fundus photographs: Validation of a deep learning algorithm in a prospective non‐interventional study in KenyaDiabetes, Obesity and Metabolism, 2024
- Development and validation of a deep-learning model to predict 10-year atherosclerotic cardiovascular disease risk from retinal images using the UK Biobank and EyePACS 10K datasetsCardiovascular Digital Health Journal, 2024
- Pivotal trial of a deep-learning-based retinal biomarker (Reti-CVD) in the prediction of cardiovascular disease: data from CMERC-HIJournal of the American Medical Informatics Association, 2023
- Longitudinal changes in the disability due to glaucoma in UzbekistanOftalmologicheskii Zhurnal, 2022
- Artificial intelligence in retinal imaging for cardiovascular disease prediction: current trends and future directionsCurrent Opinion in Ophthalmology, 2022
- Retinal arteriolar tortuosity and fractal dimension are associated with long-term cardiovascular outcomes in people with type 2 diabetesDiabetologia, 2021
- Retinal Vascular Fractal Dimensions and Their Association with Macrovascular Cardiac DiseaseOphthalmic Research, 2021