Skip to main content
Fig. 5 | BMC Cancer

Fig. 5

From: MRI-based random survival Forest model improves prediction of progression-free survival to induction chemotherapy plus concurrent Chemoradiotherapy in Locoregionally Advanced nasopharyngeal carcinoma

Fig. 5

Curve chart of the error rate of the RSF model and importance bar chart of the most important features. Note: A Curve chart of the error rate of the RSF model. The abscissa is the number of survival trees, and the ordinate is the error rate of the model in the training set. It can be observed that when there are more than 20 trees in the forest, the error rate tends to be stable and maintains around 0.1-0.3. B Importance bar chart of the most important features. The importance order of the most important radiomics features for the RSF model in predicting the PFS. The RSF model is constructed according to the optimal parameter ntree to obtain the importance of each predictive variable, and sorting is conducted based on the importance score in the order of the largest to the smallest

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us