Fig. 3: Performance comparison between AUTOSurv and other machine learning methods in two non-TCGA datasets: ICGC-OVAU and Caldas-BC. | npj Precision Oncology

Fig. 3: Performance comparison between AUTOSurv and other machine learning methods in two non-TCGA datasets: ICGC-OVAU and Caldas-BC.

From: Autosurv: interpretable deep learning framework for cancer survival analysis incorporating clinical and multi-omics data

Fig. 3: Performance comparison between AUTOSurv and other machine learning methods in two non-TCGA datasets: ICGC-OVAU and Caldas-BC.The alternative text for this image may have been generated using AI.

a the “mRNA + miRNA + clinical” case in ICGC-OVAU dataset; b the “miRNA + clinical” case in ICGC-OVAU dataset; c the “mRNA + clinical” case in ICGC-OVAU dataset; d the “mRNA + clinical” case in Caldas-BC dataset, which does not have miRNA expression data. CoxPH-ENet Cox Proportional Hazard model with Elastic Net, RSF Random Survival Forest, XGB-AFT Extreme Gradient Boosting with Accelerated Failure Time, XGB-Cox Extreme Gradient Boosting with CoxPH. The p-value from two-sided Wilcoxon signed-rank test (i.e., null hypothesis \({{\rm{H}}}_{0}\): median difference is equal to 0; versus alternative hypothesis \({{\rm{H}}}_{{\rm{A}}}\): median difference is not 0) is displayed between boxes.

Back to article page