Skip to main content
Fig. 2 | BMC Cancer

Fig. 2

From: Artificial neural network model to predict post-hepatectomy early recurrence of hepatocellular carcinoma without macroscopic vascular invasion

Fig. 2

a ROC curves for the ANN model and the eight prognostic factors used to predict PHER. b The importance of the eight prognostic factors relative to the ANN model. c Prediction probability histograms for the ANN model in HCC patients without macroscopic vascular invasion. d ROC curves for the ANN model in predicting PHER in the derivation and validation cohorts. Calibration curves of the ANN model in the derivation e and validation f cohorts. The x-axis represents deciles of predicted risk, and the y-axis indicates predicted and actual probabilities of PHER. Abbreviations: ANN, artificial neural network; PHER, post-hepatectomy early recurrence; HCC, hepatocellular carcinoma; ROC, receiver operating characteristic

Back to article page

BMC Cancer

ISSN: 1471-2407

Contact us