Anti-Mullerian hormone as a predictor of pregnancy following IVF

This single-centre retrospective observational study was performed at a university IVF centre. The aim was to examine the predictive power of AMH concentrations for clinical pregnancy rate (CPR) and establish a cut-off concentration of AMH below which no pregnancies were achieved. Data from 820 women with one treatment cycle each were analysed. There was a significant difference in CPR (24.4% and 40.0%; P < 0.01) between the lowest and highest quartiles of AMH. This study failed to establish a cut-off concentration of AMH below which there were no clinical pregnancies as several pregnancies were achieved despite an AMH less than 1 pmol/l. Log AMH showed a strong positive correlation with number of oocytes retrieved (r = 0.522; P < 0.001). Log AMH and overall CPR were weakly correlated (r = 0.112, P < 0.001), but this was not maintained when controlled for the number of oocytes. Age was a stronger independent predictor of CPR than AMH. In conclusion, although an excellent marker of ovarian response, AMH is only a weak predictor of clinical pregnancy. With AMH below the third percentile, CPR was 15%. However AMH is very useful for patient counselling and assessment when used in conjunction with age. (C) 2012, Reproductive Healthcare Ltd. Published by Elsevier Ltd. All rights reserved.