Deqi Sensation to Predict Acupuncture Effect on Functional Dyspepsia: A Machine Learning Study

Figure 3

Results of classification analyses. (a–d) The frequency distribution of accuracy, specificity, sensitivity, and AUC after 1000 iterations in the SVC model. (e) The ROC curves of the SVC model for 1000 iterations, with each line representing one iteration. (f) Real AUC was significantly higher than pseudo-AUC generated by permutation testing (). (g) Real accuracy was significantly higher than pseudo accuracy generated by Permutation testing (). AUC, area under the receiver-operating characteristic curve; ROC, receiver-operating characteristic. SVC, support vector classification.