Development and validation of a clinical prediction model for blastocyst formation during IVF/ICSI-ET

This study aims to create and validate a clinical model that predict the probability of blastocyst formation in IVF/ICSI-ET cycles.

This study employed a retrospective methodology, gathering data from 4961 cleavage-stage embryos that cultured in the reproductive center's of the Fourth Hospital of Hebei Medical University between June 2020 and March 2024. 3472 were in the training set and 1489 were in the validation set when it was randomly split into the training set and validation set in a 7:3 ratio. The study employed both univariate and multivariate logistic regression analysis to determine the factors those influence in the process of blastocyst formation. Based on the multiple regression model, a predictive model of blastocyst formation during IVF was created. The calibration and decision curves were used to assess the effectiveness and therapeutic usefulness of this model.

The following factors independently predicted the probability of blastocyst formation: the method of insemination, number of oocytes retrieved, pronuclear morphological score, the number of cleavage ball, cleavage embryo symmetry, fragmentation rate and morphological score and basal P levels of female. The receiver operating characteristic curve's area under the curve (AUC) in the training set is 0.742 (95% CI: 0.724,0.759), while the validation set's AUC is 0.729 (95% CI: 0.703,0.755), indicating a rather high clinical prediction capacity.

Our generated nomogram has the ability to forecast the probability of blastocyst formation in IVF, hence can assist clinical staff in making informed decisions.