Table 2.

The performance of the three machine learning models at predicting graft detachment in the test dataset.

Prediction model	AUC	Sensitivitya	Specificity
LASSO logistic regression	0.70	0.70	0.65
Classification tree analysis	0.65	0.65	0.62
Random forest classifier	0.72	0.68	0.62

AUC area under the curve, LASSO least absolute shrinkage and selection operator.

^aSensitivity measures the proportion of detachments that are correctly predicted as detachments.