Background: Overweight, obesity, and type 2 diabetes (T2DM) increase the risk of vascular complications, including retinal vascular alterations. Artificial intelligence (AI)-based retinal screening enables early detection of microvascular damage, potentially contributing to appropriate cardiometabolic prevention strategies. We performed a realworld evidence observational study to assess cardiometabolic parameters as well as retinal vascular alterations using novel AI-based retinal imaging.Methods: Between September and December 2025, we recruited 301 consecutive adults with overweight,obesity, or T2DM; cardiometabolic assessment was performed, and all participants also underwent retinal screening with the Aireen AI system, distinguishing those who resulted positive (n = 42), negative (n = 204), or undetermined (n = 55) at the screening.Results: All patients who resulted positive at the screening were confirmed with a diagnosis of retinal alterations by the ophthalmologists. The presence of positive retinal screening (RS+) progressively increased with worsening fasting glycemia, glycated hemoglobin (HbA1c) levels, carotid intima-media thickness, and endothelial function (P < 0.001 for all). Multivariate logistic regression analysis revealed independent associations of RS+ with HbA1c [odds ratio (OR) 2.29, P < 0.001], carotid stenosis (OR 1.06, P < 0.001), fasting glucose (OR 1.02, P < 0.001), and the triglyceride/high-density lipoprotein cholesterol ratio (OR 2.19, P = 0.010).Conclusions: These findings suggest that AIbased retinal screening with advanced tools can effectively identify early microvascular damage in individuals with overweight, obesity, or T2DM, with RS+ prevalence reflecting glycemic burden and vascular dysfunction. Therefore, integrating AI retinal assessment into cardiometabolic prevention programs may enable timely interventions to prevent progression to vision-threatening complications and support comprehensive cardiovascular risk management.

Diabetes mellitus represents a major public health challenge in Saudi Arabia. This study investigated the associations of gender, age, body mass index (BMI), and serum iron levels with diabetes risk across 13 Saudi cities and developed a machine-learning model for diabetes prediction. Data from 49,259 individuals were obtained from Al Borg Laboratories for the period 2015-2023. Descriptive statistics, independent-samples t-tests, chi-squared tests, and correlation analyses were performed. Logistic Regression, Random Forest, and Gradient Boosting models were evaluated using gender, age, BMI, and serum iron as predictors. The best-performing model was optimized through grid search with five-fold cross-validation. The cohort had a mean age of 45.92 years, mean BMI of 27.33 kg/m[2], and mean serum iron concentration of 87.11 µg/dL. The prevalence of diabetes was 10.31% and was higher among males than females (11.42% vs. 9.24%). Individuals with diabetes had significantly lower serum iron concentrations than those without diabetes (79.76 vs. 88.26 µg/dL; P < 0.001), and gender was significantly associated with diabetes status (P < 0.001). Random Forest demonstrated the best predictive performance, with an accuracy of 0.92, precision of 0.90, recall of 0.94, and area under the receiver operating characteristic curve of 0.96. Following hyperparameter tuning, the optimized model achieved a test-set accuracy of 0.90. Overall, gender, age, BMI, and serum iron levels were significantly associated with diabetes in the Saudi population, with lower serum iron levels linked to a higher prevalence of the disease. The optimized Random Forest model may provide a useful tool for diabetes risk prediction, supporting the potential application of machine learning in early detection and prevention. These findings also highlight the importance of monitoring iron status and developing tailored strategies for individuals with diabetes.