Table 3 Results of the predictive modeling for the combined radiomics and clinical features. XGBoost: eXtreme Gradient Boosting; LSVM: Lagrangian Support Vector Machine; Quest: Random Trees, and Quick, Unbiased, Efficient Statistical Tree; MLP-NN: multiplayer layer perceptron neural network; RBF-NN: radial basis function neural network
From: Clinical and radiomics feature-based outcome analysis in lumbar disc herniation surgery
Algorithm | Accuracy | |
|---|---|---|
Random Trees | Training | 100 |
XGBoost Tree | 100 | |
LSVM | 89.06 | |
SVM | 90.77 | |
CHAID | 93.75 | |
MLP-NN | 91.9 | |
RBF-NN | 87.7 | |
Testing | ||
Random Trees | 88.63 | |
XGBoost Tree | 91.19 | |
LSVM | 84.27 | |
SVM | 89.08 | |
CHAID | 85.33 | |
MLP-NN | 88.0 | |
RBF-NN | 90.7 |