Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders

Ioana Bica, Ahmed Alaa, Mihaela Van Der Schaar
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:884-895, 2020.

Abstract

The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are no hidden confounders, an assumption that is not testable in practice and, if it does not hold, leads to biased estimates. In this paper, we develop the Time Series Deconfounder, a method that leverages the assignment of multiple treatments over time to enable the estimation of treatment effects in the presence of multi-cause hidden confounders. The Time Series Deconfounder uses a novel recurrent neural network architecture with multitask output to build a factor model over time and infer latent variables that render the assigned treatments conditionally independent; then, it performs causal inference using these latent variables that act as substitutes for the multi-cause unobserved confounders. We provide a theoretical analysis for obtaining unbiased causal effects of time-varying exposures using the Time Series Deconfounder. Using both simulated and real data we show the effectiveness of our method in deconfounding the estimation of treatment responses over time.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-bica20a, title = {Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders}, author = {Bica, Ioana and Alaa, Ahmed and Van Der Schaar, Mihaela}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {884--895}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/bica20a/bica20a.pdf}, url = {https://proceedings.mlr.press/v119/bica20a.html}, abstract = {The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are no hidden confounders, an assumption that is not testable in practice and, if it does not hold, leads to biased estimates. In this paper, we develop the Time Series Deconfounder, a method that leverages the assignment of multiple treatments over time to enable the estimation of treatment effects in the presence of multi-cause hidden confounders. The Time Series Deconfounder uses a novel recurrent neural network architecture with multitask output to build a factor model over time and infer latent variables that render the assigned treatments conditionally independent; then, it performs causal inference using these latent variables that act as substitutes for the multi-cause unobserved confounders. We provide a theoretical analysis for obtaining unbiased causal effects of time-varying exposures using the Time Series Deconfounder. Using both simulated and real data we show the effectiveness of our method in deconfounding the estimation of treatment responses over time.} }
Endnote
%0 Conference Paper %T Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders %A Ioana Bica %A Ahmed Alaa %A Mihaela Van Der Schaar %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-bica20a %I PMLR %P 884--895 %U https://proceedings.mlr.press/v119/bica20a.html %V 119 %X The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are no hidden confounders, an assumption that is not testable in practice and, if it does not hold, leads to biased estimates. In this paper, we develop the Time Series Deconfounder, a method that leverages the assignment of multiple treatments over time to enable the estimation of treatment effects in the presence of multi-cause hidden confounders. The Time Series Deconfounder uses a novel recurrent neural network architecture with multitask output to build a factor model over time and infer latent variables that render the assigned treatments conditionally independent; then, it performs causal inference using these latent variables that act as substitutes for the multi-cause unobserved confounders. We provide a theoretical analysis for obtaining unbiased causal effects of time-varying exposures using the Time Series Deconfounder. Using both simulated and real data we show the effectiveness of our method in deconfounding the estimation of treatment responses over time.
APA
Bica, I., Alaa, A. & Van Der Schaar, M.. (2020). Time Series Deconfounder: Estimating Treatment Effects over Time in the Presence of Hidden Confounders. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:884-895 Available from https://proceedings.mlr.press/v119/bica20a.html.

Related Material