Development of an IVF prediction model for donor oocytes: a retrospective analysis of 9,384 embryo transfers

Abstract

Study question: Can we develop a prediction model for the chance of a live birth following transfer of an embryo created using donated oocytes? Summary answer: Three primary models that included patient, past treatment and cycle characteristics were developed to predict the chance of a live birth following transfer of an embryo created using donated oocytes; these models were well calibrated to the population studied and achieved reasonable predictive power. What is known already: Nearly 9% of assisted reproductive technology (ART) embryo transfer cycles performed globally use embryos created using donated oocytes. This percentage rises to one quarter and one half in same-sex couples and women aged over 45 years respectively. Study design, size, duration: This study uses population-based Australian clinical registry data comprising 9,384 embryo transfer cycles that occurred between 2015 and 2021. Participants/materials, setting, methods: Three prediction models were compared that incorporated patient characteristics, but differed in whether they considered use of prior autologous treatment factors and current treatment parameters. We evaluated the models using grouped cross validation and report several measures of model discrimination and calibration. Variable importance was measured through calculating the change in predictive performance that resulted from variable permutation. Main results and the role of chance: The best performing model has an AUC-ROC of 0.60 and Brier score of 0.20. While this indicates approximately 15% less discriminatory ability compared to models assessed on an autologous cohort from the same population the performance of the models was clearly statistically significantly better than random and well calibrated to the population studied. The most important variables for predicting the chance of a live birth were the oocyte donor age, number of prior oocyte recipient embryo transfer cycles and whether the transferred embryo was cleavage or blastocyst stage. Of lessor importance were the oocyte recipient parity, whether donor or partner sperm was used, the number of prior autologous embryo transfer cycles and the number of embryos transferred. Limitations, reasons for caution: The variation in donor oocyte cohorts across countries due to differences in whether anonymous and compensated donation are allowed may necessitate the models be re-calibrated prior to application in non-Australian cohorts. Wider implications of the findings: These results confirm the well-established importance of oocyte age and ART treatment history as the key prognostic factors in predicting treatment outcomes. One of the developed models has been incorporated into a consumer-facing website (YourIVFSuccess.com.au/Estimator) to allow patients to obtain personalised estimates of their chance of success using donor oocytes.