Table 3.

Main studies about risk of surgery cancellation

Author, year	Country	Study design	Type of procedure	Main outcomes	Objective	Final Cohort	Type of AI	Prediction Performance	External validation
Zhang F. J Healthc Eng. 2021.	China	Observational, retrospective, monocentric study	Elective urologic surgeries	Risk of surgeries cancellation	Identification of surgeries with high cancellation risk	5 125 cases	Random Forest, logistic regression, XGBoost-tree, support vector machine-linear, and neural networks.	The average AUCs in the test set exceeded 0.65, with the maximum of AUC (0.7199, RF, original sampling, and backward selection strategy).	No
Luo L. Health Informatics J. 2020 Mar.	China	Observational, retrospective, monocentric study	Elective urologic surgeries	Risk of surgeries cancellation	Identification of surgeries with high risks of cancellation	5 125 cases	Random Forest, XGBoost linear and tree, SVM linear and radial.	The optimal performances of the identification models were as follows: sensitivity − 0.615; specificity − 0.957; positive predictive value − 0.454; negative predictive value − 0.904; accuracy − 0.647; and area under the receiver operating characteristic curve − 0.682. The random forest model achieved the best performance.	No

AUC: Area under the Curve. RF: Random Forest. SVM: Support Vector Machine