Abstract:Aim To explore the correlation between coronary artery calcification score (CACS) and retinal arteriosclerosis using artificial intelligence assisted analysis software. Methods 511 examinees who underwent physical examinations in the Department of Health Medicine of General Hospital of Eastern Theater Command in 2022 were selected as the research subjects, they were divided into a coronary artery calcification (CAC) group (＞0,1 cases) and a non CAC group (＝0,0 cases) based on the Agatston score, the clinical data of the two groups of examinees were compared using independent sample t-tests and chi square tests. According to the condition of retinal arteriosclerosis, the examinees were divided into three groups:normal retinal artery group, weakened retinal artery elasticity group and retinal arteriosclerosis group. Kruskal Wallis H test was used to compare the quantitative indicators of CACS and retinal microvasculature among the three groups; Spearman correlation analysis was used to study the correlation between CAC grading and clinical indicators, as well as quantitative indicators of retinal microvasculature; binary Logistic regression was used to analyze the correlation between retinal arteriosclerosis and CAC. Results The age, number of smokers, waist circumference, hip circumference, waist to hip ratio (WHR), body mass index (BMI), systolic blood pressure, serum creatinine (SCr), blood uric acid (BUA), blood urea nitrogen (BUN), fasting blood glucose (FBG), glycosylated hemoglobin (HbA1c), triglyceride (TG) in the CAC group were higher than those in the non CAC group, and the difference was statistically significant (all P＜0.05). There were statistically significant differences in total CACS and AVR among the three groups of normal retina, weakened retinal artery elasticity and retinal arteriosclerosis (all P＜0.05), while there was no significant difference in CRAE and CRVE (all P＞0.05). The CACS level and total score were positively correlated with age, smoking status, waist circumference, hip circumference, WHR, BMI, systolic blood pressure, BUN, SCr, BUA, homocysteine (Hcy), FBG, 2 hour postprandial blood glucose (2h PBG), HbA1c, TG (all P＜0.05), and negatively correlated with gender, total cholesterol (TC), high density lipoprotein cholesterol (HDLC; all P＜0.05), but not with diastolic blood pressure and low density lipoprotein cholesterol (LDLC; all P＞0.05). The degree of retinal arteriosclerosis was positively correlated with age, waist circumference, hip circumference, WHR, BMI, systolic blood pressure, diastolic blood pressure, calcification scores of left main artery (LM), left anterior descending artery (LAD), left circumflex artery (LCX), right coronary artery (RCA), total CACS, BUN, FBG, 2h PBG, HbA1c and TG (all P＜0.05), and negatively correlated with TC, HDLC and LDLC (all P＜0.05), but not with gender, smoking status, pulse, SCr, BUA and Hcy (all P＞0.05). CAC level was negatively correlated with AVR (r＝－0.166, P＜0.05), and positively correlated with retinal arteriosclerosis level (r＝0.199, P＜0.05), but not significantly correlated with CRAE and CRVE (all P＞0.05). There was a correlation between CAC and retinal arteriosclerosis (P＜0.001). After adjusting for age, gender, smoking status, WHR, BMI, systolic blood pressure, FBG, SCr, BUA, BUN, and HDLC factors, the correlation between CAC and retinal arteriosclerosis still exists (P＝0.048). Conclusion AI assisted analysis of retinal vascular diameter and degree of retinal arteriosclerosis is related to CAC, which plays a positive role in risk assessment of atherosclerotic heart disease.
