ИСКУССТВЕННЫЙ ИНТЕЛЛЕКТ В ОЦЕНКЕ СОСУДИСТЫХ ИЗМЕНЕНИЙ НА ГЛАЗНОМ ДНЕ: ВОЗМОЖНОСТИ РАННЕЙ ДИАГНОСТИКИ СЕРДЕЧНО-СОСУДИСТОГО РИСКА

Бахритдинова Ф.А., Максудова З.Р., Маткаримов А.К.

Передовая Офтальмология · 2025-yil

Annotatsiya

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.

Maqola ma’lumotlari
MualliflarБахритдинова Ф.А., Максудова З.Р., Маткаримов А.К.
JurnalПередовая Офтальмология
Nashr sanasi2025-11-06
Jild14
Son3
Betlar32-38
DOI10.57231/j.ao.2025.14.3.006

Передовая Офтальмология jurnalidan boshqa maqolalar

Передовая Офтальмология — barcha maqolalar