Table 6 Summary of the feature selection and prediction methods used, if (*) method is used for classification, (**) used for survival, otherwise method is used for both classification and survival.

VAR*

Variance

GNB*

Gaussian naïve baye

RELF*

Relief

MNB*

MultinomiIive bayes

MI*

Mutual information

BNB*

Bernoulli naïve bayes

mRMR*

Minimum redundancy maximum relevance ensemble

KNN*

K-nearest neighbourhood

ETE*

Extra tree ensemble

RF*

Random forest

GBDT*

Gradient boosting decision tree

BAG*

Bagging

TSQ*

T-test score

DT*

Decision tree

CHSQ*

Chi-square score

GBDT*

Gradient boosting decision tree

EN*

Elastic net

Adaboost*

Adaptive boosting

LASSO*

Least absolute shrinkage and selection operator

XGB*

Xgboost

WLCX*

Wilcoxon

LDA*

Linear discriminant analysis

L¹-SVM*

L¹- based linear support vector machine

LGR*

Logistic regression

L¹-LGR*

L¹ -based logistic regression

Linear-SVM*

Linear support vector machine

JMIM**

Joint mutual information maximisation

RBF-SVM*

Radial basis function support vector machine

RFVH**

Random forest with variable hunting

MLPC*

Multi-layer perceptron

RFVH -IMP**

Random forest with variable hunting and Gini impurity corrected variable importance

BGLM_CoxPH**

Boosting gradient linear models

RF*

Random forest variable hunting with maximal depth

BGLM_Cindex**

Boosting gradient linear models

Spearman**

Spearman correlation

BGLM_Weibull**

Boosting gradient linear models

Person**

Pearson correlation

BT_CoxPH**

Boosting trees

Kendall**

Kendall rank correlation

BT_Weibull**

Boosting trees

Random**

Random (null hypothesis)

Cox_Lasso**

Cox lasso

Cox_Net**

Cox net

Cox**

Cox proportional hazard

RSF**

Random survival forest

MSR_RF**

Random forest using maximally selected rank statistics

ET_RF**

Random forest with extra trees