Abstract: Objective To explore the risk factors for coronary artery disease （CAD） in patients with obstructive sleep apnea （OSA） and to establish a clinical risk prediction model based on the systemic inflammatory response index （SIRI） and to validat its effectiveness. Methods OSA patients suspected of CAD who underwent coronary angiography or coronary CT angiography at the First Affiliated Hospital of Xinjiang Medical University between April 2020 and December 2023 were enrolled. Patients were divided into CAD and non-CAD groups based on the degree of coronary artery stenosis. Variable were screened using LASSO regression and multifactor logistic regression, and a nomogram was constructed. The discrimination and calibration of the prediction model were evaluated and validated using receiver operating characteristic （ROC） curves, calibration curves, and Hosmer-Lemeshow test. The clinical effectiveness of the prediction model was assessed using decision curve analysis （DCA）. Results Multivariate logistic regression results indicated the following factors for CAD in OSA patients （all P < 0.05）： age≥50 years（OR=1.947 （95% CI 1.277-2.969））, hypertension （OR=2.462 （95% CI 1.612-3.761））, diabetes （OR=2.003 （95% CI 1.313-3.057））, low-density lipoprotein cholesterol （LDL-C） ≥2.6 mmol/L （OR=1.793 （95% CI 1.176-2.735））, apnea-hypopnea index （AHI） ≥30 times/hour （OR=2.425 （95% CI 1.500-3.920））, and SIRI ≥0.84 （OR=2.240 （95% CI 1.463-3.428））. A nomogram was constructed based on these factors. The area under the ROC curve （AUC） for the prediction model was 0.721 （95% CI 0.673-0.770） in the training set and 0.750 （95% CI 0.678-0.820） in the validation set. Calibration curves and the Hosmer-Lemeshow test indicated good agreement between predicted and actual outcomes （training set： χ ² = 7.924, P = 0.542； validation set： χ ² = 12.304, P = 0.197）. DCA demonstrated the clinical utility of the prediction model. Conclusion A risk prediction model incorporating age, hypertension, diabetes, LDL-C, AHI, and SIRI has potential clinical value for predicting CAD in OSA patients.