Deep Survival Analysis: Nonparametrics and Missingness

Xenia Miscouridou, Adler Perotte, Noemie Elhadad, Rajesh Ranganath
Proceedings of the 3rd Machine Learning for Healthcare Conference, PMLR 85:244-256, 2018.

Abstract

Clinical care requires understanding the time to medical events. Medical events include the time to a disease like chronic kidney disease progressing or the time to a complication as in stroke for high blood pressure. Models for event times live in the framework provided by survival analysis. We expand on deep survival analysis, a deep generative model for survival analysis in the presence of missing data, where the survival times are modeled using Weibull distributions. We develop methods to relax the distributional assumptions in deep survival analysis using survival distributions that can approximate any true survival function. We show that the model structure mimics the information-optimal procedure in the presence of missing data. Our experiments demonstrate that moving to flexible survival functions yields better likelihoods and concordances for coronary heart disease prediction from electronic health records.

Cite this Paper

BibTeX
@InProceedings{pmlr-v85-miscouridou18a, title = {Deep Survival Analysis: Nonparametrics and Missingness}, author = {Miscouridou, Xenia and Perotte, Adler and Elhadad, Noemie and Ranganath, Rajesh}, booktitle = {Proceedings of the 3rd Machine Learning for Healthcare Conference}, pages = {244--256}, year = {2018}, editor = {Doshi-Velez, Finale and Fackler, Jim and Jung, Ken and Kale, David and Ranganath, Rajesh and Wallace, Byron and Wiens, Jenna}, volume = {85}, series = {Proceedings of Machine Learning Research}, month = {17--18 Aug}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v85/miscouridou18a/miscouridou18a.pdf}, url = {https://proceedings.mlr.press/v85/miscouridou18a.html}, abstract = {Clinical care requires understanding the time to medical events. Medical events include the time to a disease like chronic kidney disease progressing or the time to a complication as in stroke for high blood pressure. Models for event times live in the framework provided by survival analysis. We expand on deep survival analysis, a deep generative model for survival analysis in the presence of missing data, where the survival times are modeled using Weibull distributions. We develop methods to relax the distributional assumptions in deep survival analysis using survival distributions that can approximate any true survival function. We show that the model structure mimics the information-optimal procedure in the presence of missing data. Our experiments demonstrate that moving to flexible survival functions yields better likelihoods and concordances for coronary heart disease prediction from electronic health records.} }
Endnote
%0 Conference Paper %T Deep Survival Analysis: Nonparametrics and Missingness %A Xenia Miscouridou %A Adler Perotte %A Noemie Elhadad %A Rajesh Ranganath %B Proceedings of the 3rd Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2018 %E Finale Doshi-Velez %E Jim Fackler %E Ken Jung %E David Kale %E Rajesh Ranganath %E Byron Wallace %E Jenna Wiens %F pmlr-v85-miscouridou18a %I PMLR %P 244--256 %U https://proceedings.mlr.press/v85/miscouridou18a.html %V 85 %X Clinical care requires understanding the time to medical events. Medical events include the time to a disease like chronic kidney disease progressing or the time to a complication as in stroke for high blood pressure. Models for event times live in the framework provided by survival analysis. We expand on deep survival analysis, a deep generative model for survival analysis in the presence of missing data, where the survival times are modeled using Weibull distributions. We develop methods to relax the distributional assumptions in deep survival analysis using survival distributions that can approximate any true survival function. We show that the model structure mimics the information-optimal procedure in the presence of missing data. Our experiments demonstrate that moving to flexible survival functions yields better likelihoods and concordances for coronary heart disease prediction from electronic health records.
APA
Miscouridou, X., Perotte, A., Elhadad, N. & Ranganath, R.. (2018). Deep Survival Analysis: Nonparametrics and Missingness. Proceedings of the 3rd Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 85:244-256 Available from https://proceedings.mlr.press/v85/miscouridou18a.html.

Related Material