Development and validation of a novel predictive model and web calculator for evaluating transfusion risk after spinal fusion for spinal tuberculosis: a retrospective cohort study

Table 3 Predictive performance of nomogram and machine learning algorithms

Model	Average AUC	Maximum AUC	Average Accuracy
Nomogram	0.75	0.93
Support vector machine	0.62	0.68	0.62
K-nearest neighbors	0.65	0.77	0.71
Decision tree	0.56	0.60	0.64
Naive Bayesian	0.74	0.88	0.73
Multilayer perceptron	0.56	0.63	0.65
Random Forest	0.72	0.83	0.75

ISSN: 1471-2474