The average individual ROC AUC scores are the average scores on the test set after 50 training iterations each with a different randomly allocated train/validation/test split with 25 embryos in the successful class and 48 embryos in the unsuccessful class for both the test and validation set. The accompanying errors are the standard error across these 50 training attempts. For the ROC AUC using average confidence score, the average confidence score was first calculated from 50 models (using 5-fold cross-validation and 50 training attempts) and these average confidence scores were then used to calculate the ROC AUC.