Objective: To investigate the influence and predictive efficiency of endometrial morphology and spiral artery blood flow parameters on assisted reproductive pregnancy outcomes in patients with polycystic ovary syndrome (PCOS). Methods: A total of 84 PCOS patients who received artificial insemination with husband sperm in the hospital were prospectively selected as research subjects. In the assisted pregnancy cycle, the endometrial morphology classification was evaluated by unified transvaginal ultrasound on the day of artificial insemination, and the spiral artery blood flow parameters [pulsatility index (PI), resistance index (RI), peak systolic velocity/peak diastolic velocity (S/D)] were measured. According to the pregnancy outcomes, they were divided into successful pregnancy group (n=40) and failed pregnancy group (n=44). The differences in the above indicators were compared between the two groups. Multivariate logistic regression analysis was used to analyze the influencing factors of assisted reproductive pregnancy outcomes in PCOS patients. The area under the receiver operating characteristic (ROC) curve (AUC) was used to evaluate the predictive value of various indicators alone and in combination on pregnancy outcomes. Results: The type A endometrium in failed pregnancy group was lower than that in successful pregnancy group, and the type C endometrium, PI, RI and S/D were higher than those in successful pregnancy group (P<0.05). B/C endometrial morphology, PI, RI and S/D were risk factors of assisted reproductive pregnancy failure in PCOS patients (P<0.05). The AUCs of B/C endometrial morphology, PI, RI and S/D for predicting assisted reproductive pregnancy failure were 0.700 [95%CI=0.586-0.814], 0.801 [95%CI=0.700-0.901], 0.693 [95%CI=0.579-0.807] and 0.791 [95%CI=0.698-0.885], and the AUC of combined prediction was increased to 0.908 [95%CI=0.845-0.971]. Conclusion: Endometrial morphology and spiral artery blood flow parameters are closely related to the failure of artificial insemination assisted pregnancy in PCOS patients, and combined detection of multiple parameters has high clinical value on predicting the failure of assisted pregnancy.