Fig. 3: Construction of a prognostic signature using MRGs via machine learning. | npj Precision Oncology

Fig. 3: Construction of a prognostic signature using MRGs via machine learning.

From: Bladder cancer diagnostic and prognostic models from DNA methylation by multi algorithm machine learning

Fig. 3: Construction of a prognostic signature using MRGs via machine learning.The alternative text for this image may have been generated using AI.

A SVM-RFE analysis. B Lasso regression analysis. C Random forest analysis. D Boruta feature selection analysis. E XGBoost analysis. F PAMR analysis. G A total of 62 MRGs were supported by more than one algorithm. K Univariate Cox regression analysis identified 11 significant MRGs (P < 0.05).

Back to article page