Reusability report: Prostate cancer stratification with diverse biologically-informed neural architectures
This work addresses reproducibility and model sensitivity in clinical prediction tasks for prostate cancer, but is incremental as it builds on prior research.
The study verified the reproducibility of a biologically-informed neural network for prostate cancer stratification and explored alternative architectures, finding that different neural architectures make persistent incorrect predictions for individual patients, indicating sensitivity to different data aspects.
In Elmarakeby et al., "Biologically informed deep neural network for prostate cancer discovery", a feedforward neural network with biologically informed, sparse connections (P-NET) was presented to model the state of prostate cancer. We verified the reproducibility of the study conducted by Elmarakeby et al., using both their original codebase, and our own re-implementation using more up-to-date libraries. We quantified the contribution of network sparsification by Reactome biological pathways, and confirmed its importance to P-NET's superior performance. Furthermore, we explored alternative neural architectures and approaches to incorporating biological information into the networks. We experimented with three types of graph neural networks on the same training data, and investigated the clinical prediction agreement between different models. Our analyses demonstrated that deep neural networks with distinct architectures make incorrect predictions for individual patient that are persistent across different initializations of a specific neural architecture. This suggests that different neural architectures are sensitive to different aspects of the data, an important yet under-explored challenge for clinical prediction tasks.