Skip to main content

Table 3 Performance metrics of machine learning models to predict the progression-free survival of second-line paclitaxel in patients with advanced gastric cancer

From: Integrated clinical and genomic models using machine-learning methods to predict the efficacy of paclitaxel-based chemotherapy in patients with advanced gastric cancer

Models

AUROC

Sensitivity

Specificity

Accuracy

F1 score

RF

0.499

0.517

0.417

0.588

0.417

LR

0.679

0.638

0.375

0.823

0.461

ANN

0.618

0.500

0.706

0.621

0.522

ANN with GE

0.732

0.458

0.912

0.724

0.579

  1. RF, random forest; LR, logistic regression; ANN, artificial neural network; ANN with GE, artificial neural network with genetic embedding
Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us