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

Figure 4

Results of prediction analyses. (a) The frequency distribution of MSE after 1000 iterations in the SVR model. (b) The frequency distribution of R² after 1000 iterations in the SVR model. (c and e) The correlation scatterplots between the actual values and predicted values, the scatterplots for the best predictive performance (Max), the average predictive performance (Mean), and the worst predictive performance (Min) in the 1000 repetitions were plotted, respectively. (f) Real MSE was significantly lower than pseudo-MSE generated by Permutation testing (). (g) Real R² was significantly higher than pseudo R² generated by Permutation testing (). SVR, support vector regression; MSE, mean squared error; R², coefficient of determination.