Single and repeated GnRH agonist stimulation tests compared with basal markers of ovarian reserve in the prediction of outcome in IVF.

Purpose: To study the value of a single or repeated GnRH agonist stimulation test (GAST) in predicting outcome in IVF compared to basal ovarian reserve tests.

Methods: A total of 57 women was included. In a cycle prior to the IVF treatment, on day 3, an antral follicle count (AFC) was performed and blood taken for basal FSH, inhibin B and E2 measurements, followed by a subcutaneous injection of 100 microg triptorelin for the purpose of the GAST. Twenty-four hours later blood sampling was repeated. All the tests were repeated in a subsequent cycle. From the GAST E2 and inhibin B response were used as test parameters. The outcome measures were poor ovarian response and ongoing pregnancy. Group comparisons were done using the Mann-Whitney or chi-square test. Univariate and multivariate logistic regression was applied to assess which test revealed the highest predictive accuracy as expressed in the area under receiver-operating characteristic curve (ROC(AUC)). Clinical value was compared by calculating classical test characteristics for the best logistic models.

Results: All the basal and GAST variables were significantly different in the poor responders (n = 19) compared to normal responders (n = 38). In the univariate analysis on cycle 1 tests the AFC was the best predictor for poor ovarian response, while in cycle 2 the E2 response in the GAST performed best (ROC(AUC) of 0.91 for both). Multivariate analysis of the basal variables led to the selection of AFC and inhibin B in cycle 1, yielding a ROC(AUC) of 0.96. Mean E2 response was selected in a multivariate analysis of the repeated GAST variables (ROC(AUC) 0.91). At a specificity level of -0.90, several logistic models including GAST variables appeared to have a sensitivity (-0.80), positive predictive value (-0.82) and false positive rate (-0.18), comparable to a logistic model containing AFC and inhibin B. None of the test variables showed a significant relation with ongoing pregnancy.

Conclusions: The GAST has a rather good ability to predict poor response in IVF. However, comparing the predictive accuracy and clinical value of the GAST with a day 3 AFC and inhibin B, it appeared that neither a single nor a repeated GAST performed better. In addition, the predictive ability towards ongoing pregnancy is poor. Therefore, the use of the GAST as a predictor of outcome in IVF should not be advocated.