Systematic Framework to Predict Early-Stage Liver Carcinoma Using Hybrid of Feature Selection Techniques and Regression Techniques

Table 9

Constant Feature Elimination-based Regression algorithms with accuracy and error rate during training and testing.

Models	Accuracy (R2-Score) training (↑)	Accuracy (R2-Score) testing (↑)	MSE training (↓)	MSE testing (↓)
Linear Regression	0.5519	0.2923	0.1262	0.1656
Ridge Regression	0.5519	0.2933	0.1262	0.1654
LASSO Regression	0.3511	0.3364	0.1518	0.1603
Elastic Net Regression	0.4078	0.4019	0.1451	0.1522
Decision Tree	0.9993	−0.0004	0.0051	0.1969
Support Vector Regression	0.707	0.1797	0.102	0.1782
Multilayer Perceptron Regression	−4303.1142	−4577.799	12.3669	13.3172
Random Forest Regression	0.8907	0.4903	0.0623	0.1405