Semi-Structured Deep Piecewise Exponential Models
This work addresses survival analysis tasks like competing risks and multi-state modeling for researchers and practitioners, though it appears incremental as it builds on existing statistical and deep learning methods.
The authors tackled survival analysis by proposing a framework that combines piecewise exponential models with deep learning to handle multiple data sources and complex interactions, demonstrating its application in predicting Alzheimer's disease progression with tabular and 3D point cloud data.
We propose a versatile framework for survival analysis that combines advanced concepts from statistics with deep learning. The presented framework is based on piecewise exponential models and thereby supports various survival tasks, such as competing risks and multi-state modeling, and further allows for estimation of time-varying effects and time-varying features. To also include multiple data sources and higher-order interaction effects into the model, we embed the model class in a neural network and thereby enable the simultaneous estimation of both inherently interpretable structured regression inputs as well as deep neural network components which can potentially process additional unstructured data sources. A proof of concept is provided by using the framework to predict Alzheimer's disease progression based on tabular and 3D point cloud data and applying it to synthetic data.