Researchers developed a prediction model to estimate the likelihood of clinical pregnancy after frozen-thawed embryo transfer (FET). The study included 218 infertile patients split into training and validation groups. They assessed common ultrasound measures before transfer, including endometrial thickness, blood flow resistance, and the direction and frequency of uterine contractions.
Several features were linked to pregnancy outcomes: thicker endometrium was associated with higher odds, while higher resistance and certain contraction patterns were linked to lower odds. The model showed good discrimination in the training set (AUC 0.828) and fit the data well, but these findings need confirmation in larger, independent groups.
This was a single-center study with a modest sample size, and it is unclear whether the validation was truly external or over time. The model has not been compared with existing approaches, and it does not prove that changing these ultrasound measures would alter pregnancy rates. For now, it suggests that routine ultrasound information may help personalize expectations after FET.