From: A multi-omics supervised autoencoder for pan-cancer clinical outcome endpoints prediction
Methods | OS | DSS | PFI | DFI |
---|---|---|---|---|
SVM | 0.6905 (±0.0108) | 0.6927 (±0.0154) | 0.6416 (±0.0119) | 0.5950 (±0.0174) |
DecisionTree | 0.6973 (±0.0082) | 0.6877 (±0.0199) | 0.6503 (±0.0093) | 0.5736 (±0.0276) |
NaĂ¯ve Bayes | 0.6825 (±0.0110) | 0.7139 (±0.0277) | 0.6672 (±0.0074) | 0.6631 (±0.0304) |
kNN | 0.7189 (±0.0086) | 0.7134 (±0.0146) | 0.6788 (±0.0095) | 0.6488 (±0.0474) |
RandomForest | 0.7355 (±0.0082) | 0.7449 (±0.0160) | 0.6999 (±0.0134) | 0.6621 (±0.0299) |
AdaBoost | 0.7297 (±0.0042) | 0.7369 (±0.0219) | 0.6831 (±0.0155) | 0.6454 (±0.0254) |
Multi-view Factorization AutoEncoder [3] | 0.766 (−) | – | 0.724 (−) | – |
MOSAE | 0.7830 (±0.0081) | 0.7870 (±0.0293) | 0.7325 (±0.0123) | 0.7061 (±0.0393) |