Predicting early postoperative PONV using multiple machine-learning- and deep-learning-algorithms

Table 2 Results of artificial intelligence algorithm forecasting early PONV in training group

Train Model name	Accuracy	Precision	Recall	F1 score	AUC
Logistic Regression	0.870	0.464	0.055	0.098	0.770
Decision Tree	0.873	0.583	0.059	0.108	0.751
SVC	0.872	0.583	0.030	0.056	0.771
gnb	0.819	0.222	0.161	0.187	0.718
knn	0.886	0.700	0.208	0.320	0.888
adab	0.871	0.487	0.081	0.138	0.819
DNN	0.886	0.765	0.165	0.272	0.872
RNN	0.907	0.743	0.428	0.543	0.929
LSTM	0.872	1.000	0.004	0.008	0.731
CNNRNN	0.873	0.800	0.017	0.033	0.746

SVC Logistic Regression, Decision Tree, Linear Support Vector, gnb Gaussian naive Bayes, knn K-nearst neighbors, adab AdaBoost, DNN Artificial Neural Networks, RNN Recurrent Neural Networks, LSTM Long Short - Term Memory, CNNRNN Convolutional Neural Network + Recurrent Neural Networks

ISSN: 1471-2288