Establishment and validation of methylation prognostic prediction model via machine learning
(A) Selection of the tuning parameter (λ) in the Lasso model. The Y-axis represents partial likelihood deviance, and the lower X-axis represents the log (λ). Numbers along the upper X-axis represent the average number of predictors. Red dots indicate average deviance values for each model with a given λ, where the model provides its best fit to data. (B) Lasso coefficient profiles of the survival-associated methylations. The gray dotted vertical line is the value selected using 10-fold cross-validation in A. (C) This part shows the Kaplan–Meier (K-M) curves for high- and low-risk groups in the training set. (D) ROC curves for patients under training set at 1, 3, and 5 years. (E) This part shows the K-M curves for high- and low-risk groups in the testing set. (F) ROC curves for patients under testing set at 1, 3, and 5 years. AUC, area under the ROC curve.