Background: This study aims to evaluate ocular changes in patients with ischemic stroke using multimodal imaging and explore the predictive value of ocular abnormalities for ischemic stroke. Methods: A total of 203 patients (ischemic stroke group, 62; control group, 141) were enrolled in this study. Basic data from patients, including age; gender; height; weight; history of hypertension, hyperlipidemia, diabetes, alcohol use, and coronary heart disease; and smoking status, were collected. Consequently, Doppler color ultrasound, color fundus photography, and optical coherence tomography (OCT) examinations were conducted. Differences in traditional risk factors and ocular parameters between the two groups were compared, and binary logistic regression was used for multivariate analysis. Results: The central retinal artery equivalent (CRAE) in the ischemic stroke group was 150.72 +/- 20.15 mu m and that in the control group was 159.68 +/- 20.05 mu m. The difference was statistically significant (P = 0.004). Moreover, the subfoveal choroidal thickness (SFChT) in the ischemic stroke group was 199.90 +/- 69.27 mu m and that in the control group was 227.40 +/- 62.20 mu m. The difference was statistically significant (P = 0.006). Logistic regression results showed that smoking [odds ratio (OR) = 2.823; 95% confidence interval (95% CI) = 1.477-5.395], CRAE (OR = 0.980; 95% CI = 0.965-0.996), and SFChT (OR = 0.994; 95% CI = 0.989-0.999) are associated with increased risk of ischemic stroke when ocular parameters were combined with traditional risk factors. The area under the receiver operating characteristic (ROC) curve was 0.726, which shows good diagnostic accuracy. Conclusion: SFChT may be a diagnostic marker for early detection and monitoring of ischemic stroke. Combined with traditional risks, retinal artery diameter, and choroidal thickness, the prediction model can improve ischemic stroke prediction.