The article explores the use of machine learning in stratifying prostate cancer. It focuses on the verification of the reproducibility of a study conducted by Elmarakeby et al., using both their original codebase and re-implementation using up-to-date libraries. The study also explores alternative neural architectures and approaches to incorporating biological information into the networks. It concludes that different neural architectures are sensitive to different aspects of the data, posing an under-explored challenge for clinical prediction.
Publication date: 28 Sep 2023
Project Page: https://arxiv.org/abs/2309.16645v1
Paper: https://arxiv.org/pdf/2309.16645
