Feature Selection for Survival Analysis with Competing Risks using Deep Learning
This work addresses a specific bottleneck in survival analysis for medical applications, representing an incremental advance.
The paper tackles the problem of deep learning models for survival analysis suffering from performance deficits due to irrelevant features, and it shows that novel feature selection methods achieve substantial performance improvements on real-world medical datasets.
Deep learning models for survival analysis have gained significant attention in the literature, but they suffer from severe performance deficits when the dataset contains many irrelevant features. We give empirical evidence for this problem in real-world medical settings using the state-of-the-art model DeepHit. Furthermore, we develop methods to improve the deep learning model through novel approaches to feature selection in survival analysis. We propose filter methods for hard feature selection and a neural network architecture that weights features for soft feature selection. Our experiments on two real-world medical datasets demonstrate that substantial performance improvements against the original models are achievable.