Skip to main content
Search

# Reproductive Biology and Fertility

1 related articles

Subscribe to updates
  1. Explainable XGBoost model predicts clinical pregnancy after frozen embryo transfer in 1,319 single-center cases, with AUC falling from 0.854 to 0.722 in temporal validation

    Using retrospective single-center data from 1,319 patients undergoing their first frozen embryo transfer at Guangdong Provincial Hospital of Chinese Medicine, split by transfer date into a training cohort (n=1,013) and a temporal validation cohort (n=306), the authors used LASSO to select age, induced abortions, cycle type, good-quality embryos, transferred embryos, endometrial change, BMI, antral follicle count, embryo transfer-day endometrial thickness, and retrieval-transfer interval, then developed an XGBoost model and compared it with logistic regression; XGBoost achieved an AUC of 0.854 (95% CI 0.832-0.877) in training and 0.722 (95% CI 0.666-0.779) in temporal validation, with AUPRC values of 0.840 and 0.707, acceptable calibration in validation (Brier score 0.212, intercept 0.

You’re all caught up