REFINED-CNN framework for survival prediction with high-dimensional features

Robust and accurate survival prediction of clinical trials using high-throughput genomics data is a funda- mental challenge in pharmacogenomics. Current machine learning tools often provide limited predictive performance and model interpretation in these settings. In the present study, we extend the application of REFINED-CNN from regression tasks to making survival predictions, by mapping high-dimensional RNA sequencing data into REFINED images which are conducive to CNN modeling. We show that the REFINED-CNN survival model can be easily adapted to new tasks of a similar nature (e.g., predicting on new cancer types) using transfer learning with a low number of patients. Furthermore, the model can also be interpreted both locally and globally through risk score back propagation that quantifies each feature (e.g., gene) importance in survival prediction task for the patient or cancer type of interest.

Automated summary

Robust and accurate survival prediction is crucial in pharmacogenomics, however, current machine learning tools lack predictive performance and model interpretability. In this study, we extend the application of REFINED-CNN to survival predictions using high-dimensional RNA sequencing data. We show that the REFINED-CNN survival model can be easily adapted to new tasks with low patient numbers, and it can provide both local and global interpretations of feature importance in survival prediction.