A Deep Neural Network for Gastric Cancer Prognosis Prediction Based on Biological Information Pathways

Figure 3

Prediction performance of the GCS-Net. (a) The AUPRC value of the GCS-Net outperforms other classical machine learning models on the test set. (b) The GCS-Net has a true negative rate (TN) of 75% and a true positive rate (TP) of 100% in the test set.

(a)

(b)