Skip to main content

Table 2 Performance of the machine learning algorithms and multiple linear regression model

From: A machine learning-based algorithm used to estimate the physiological elongation of ocular axial length in myopic children

  Algorithms R2 R RMSE MAE MSE
Traditional Statistical Method Multiple Linear Regression 0.81 0.8985 0.4380 0.3455 0.1919
Machine Learning Methods Linear Regression (linear) 0.86* 0.9276* 0.3782 0.2933 0.1430
Linear Regression (Robust) 0.86* 0.9276* 0.3780* 0.2929 0.1427*
SVM (linear) 0.86* 0.9276* 0.3781 0.2928* 0.1429
SVM (Quadratic) 0.85 0.9219 0.3916 0.3013 0.1533
SVM (Cubic) 0.82 0.9055 0.4291 0.3263 0.1841
Bagged Trees 0.77 0.8775 0.4820 0.3583 0.2323
  1. SVM = support vector machine; RMSE = root mean square error; MAE = mean absolute error; MSE = mean squared error
  2. Best values of indices are marked by an asterisk (*)