Semi-Structured Deep Piecewise Exponential Models

Philipp Kopper, Sebastian Pölsterl, Christian Wachinger, Bernd Bischl, Andreas Bender, David Rügamer
Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, PMLR 146:40-53, 2021.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v146-kopper21a, title = {Semi-Structured Deep Piecewise Exponential Models}, author = {Kopper, Philipp and P{\"o}lsterl, Sebastian and Wachinger, Christian and Bischl, Bernd and Bender, Andreas and R{\"u}gamer, David}, booktitle = {Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021}, pages = {40--53}, year = {2021}, editor = {Greiner, Russell and Kumar, Neeraj and Gerds, Thomas Alexander and van der Schaar, Mihaela}, volume = {146}, series = {Proceedings of Machine Learning Research}, month = {22--24 Mar}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v146/kopper21a/kopper21a.pdf}, url = {https://proceedings.mlr.press/v146/kopper21a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Semi-Structured Deep Piecewise Exponential Models %A Philipp Kopper %A Sebastian Pölsterl %A Christian Wachinger %A Bernd Bischl %A Andreas Bender %A David Rügamer %B Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021 %C Proceedings of Machine Learning Research %D 2021 %E Russell Greiner %E Neeraj Kumar %E Thomas Alexander Gerds %E Mihaela van der Schaar %F pmlr-v146-kopper21a %I PMLR %P 40--53 %U https://proceedings.mlr.press/v146/kopper21a.html %V 146 %X 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.
APA
Kopper, P., Pölsterl, S., Wachinger, C., Bischl, B., Bender, A. & Rügamer, D.. (2021). Semi-Structured Deep Piecewise Exponential Models. Proceedings of AAAI Spring Symposium on Survival Prediction - Algorithms, Challenges, and Applications 2021, in Proceedings of Machine Learning Research 146:40-53 Available from https://proceedings.mlr.press/v146/kopper21a.html.

Related Material