Interpretable machine learning models for predicting venous thromboembolism in the intensive care unit: an analysis based on data from 207 centers

Table 2 Performance of three machine learning models for predicting VTE in critically ill patients

Models	AUC	Accuracy	No Information Rate	Balanced Accuracy	Kappa	Precision	F1 score	Sensitivity	Specificity
RF	0.9378	0.9958	0.9858	0.8890	0.8371	0.9095	0.8393	0.7791	0.9989
XGBoost	0.9492	0.9947	0.9858	0.8894	0.8041	0.8344	0.8068	0.7810	0.9978
SVM	0.8290	0.9899	0.9858	0.7934	0.6186	0.6602	0.6237	0.5911	0.9956

AUC area under curve, RF random forest, XGBoost eXtreme gradient boosting, SVM support vector machine

ISSN: 1364-8535