Skip to main content
. 2026 Sep 21;17:1916182. doi: 10.3389/fendo.2026.1916182

Figure 2.

Figure composed of nine panels arranged in a 3 by 3 grid labeled A, B, and C, each divided into three stages: Baseline model, Stimulation model, and Embryo model. Panel A shows receiver operating characteristic (ROC) curves with AUC values comparing four machine learning models across three stages. Panel B displays calibration curves showing predicted probability against observed proportion for the same models, with perfect calibration as a reference. Panel C presents decision curve analyses showing net benefit versus threshold probability for four models and two treatment strategies. Legends and axes are clearly labeled throughout.

Performance comparison of the optimal base model and three ensemble strategies across three stages in test cohort. (A) ROC curves showing the discriminative performance at Stage 1, baseline stage; Stage 2, stimulation stage; and Stage 3 embryo development stages. (B) Calibration curves, with Brier scores noted. (C) Decision curve analysis.