G-Net: a Recurrent Network Approach to G-Computation for Counterfactual Prediction Under a Dynamic Treatment Regime

Rui Li, Stephanie Hu, Mingyu Lu, Yuria Utsumi, Prithwish Chakraborty, Daby M. Sow, Piyush Madan, Jun Li, Mohamed Ghalwash, Zach Shahn, Li-wei Lehman
Proceedings of Machine Learning for Health, PMLR 158:282-299, 2021.

Abstract

Counterfactual prediction is a fundamental task in decision-making. This paper introduces G-Net, a sequential deep learning framework for counterfactual prediction under dynamic time-varying treatment strategies in complex longitudinal settings. G-Net is based upon g-computation, a causal inference method for estimating effects of general dynamic treatment strategies. Past g-computation implementations have mostly been built using classical regression models. G-Net instead adopts a recurrent neural network framework to capture complex temporal and nonlinear dependencies in the data. To our knowledge, G-Net is the first g-computation based deep sequential modeling framework that provides estimates of treatment effects under \em{dynamic} and \em{time-varying} treatment strategies. We evaluate G-Net using simulated longitudinal data from two sources: CVSim, a mechanistic model of the cardiovascular system, and a pharmacokinetic simulation of tumor growth. G-Net outperforms both classical and state-of-the-art counterfactual prediction models in these settings.

Cite this Paper

BibTeX
@InProceedings{pmlr-v158-li21a, title = {G-Net: a Recurrent Network Approach to G-Computation for Counterfactual Prediction Under a Dynamic Treatment Regime}, author = {Li, Rui and Hu, Stephanie and Lu, Mingyu and Utsumi, Yuria and Chakraborty, Prithwish and Sow, Daby M. and Madan, Piyush and Li, Jun and Ghalwash, Mohamed and Shahn, Zach and Lehman, Li-wei}, booktitle = {Proceedings of Machine Learning for Health}, pages = {282--299}, year = {2021}, editor = {Roy, Subhrajit and Pfohl, Stephen and Rocheteau, Emma and Tadesse, Girmaw Abebe and Oala, Luis and Falck, Fabian and Zhou, Yuyin and Shen, Liyue and Zamzmi, Ghada and Mugambi, Purity and Zirikly, Ayah and McDermott, Matthew B. A. and Alsentzer, Emily}, volume = {158}, series = {Proceedings of Machine Learning Research}, month = {04 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v158/li21a/li21a.pdf}, url = {https://proceedings.mlr.press/v158/li21a.html}, abstract = {Counterfactual prediction is a fundamental task in decision-making. This paper introduces G-Net, a sequential deep learning framework for counterfactual prediction under dynamic time-varying treatment strategies in complex longitudinal settings. G-Net is based upon g-computation, a causal inference method for estimating effects of general dynamic treatment strategies. Past g-computation implementations have mostly been built using classical regression models. G-Net instead adopts a recurrent neural network framework to capture complex temporal and nonlinear dependencies in the data. To our knowledge, G-Net is the first g-computation based deep sequential modeling framework that provides estimates of treatment effects under \em{dynamic} and \em{time-varying} treatment strategies. We evaluate G-Net using simulated longitudinal data from two sources: CVSim, a mechanistic model of the cardiovascular system, and a pharmacokinetic simulation of tumor growth. G-Net outperforms both classical and state-of-the-art counterfactual prediction models in these settings.} }
Endnote
%0 Conference Paper %T G-Net: a Recurrent Network Approach to G-Computation for Counterfactual Prediction Under a Dynamic Treatment Regime %A Rui Li %A Stephanie Hu %A Mingyu Lu %A Yuria Utsumi %A Prithwish Chakraborty %A Daby M. Sow %A Piyush Madan %A Jun Li %A Mohamed Ghalwash %A Zach Shahn %A Li-wei Lehman %B Proceedings of Machine Learning for Health %C Proceedings of Machine Learning Research %D 2021 %E Subhrajit Roy %E Stephen Pfohl %E Emma Rocheteau %E Girmaw Abebe Tadesse %E Luis Oala %E Fabian Falck %E Yuyin Zhou %E Liyue Shen %E Ghada Zamzmi %E Purity Mugambi %E Ayah Zirikly %E Matthew B. A. McDermott %E Emily Alsentzer %F pmlr-v158-li21a %I PMLR %P 282--299 %U https://proceedings.mlr.press/v158/li21a.html %V 158 %X Counterfactual prediction is a fundamental task in decision-making. This paper introduces G-Net, a sequential deep learning framework for counterfactual prediction under dynamic time-varying treatment strategies in complex longitudinal settings. G-Net is based upon g-computation, a causal inference method for estimating effects of general dynamic treatment strategies. Past g-computation implementations have mostly been built using classical regression models. G-Net instead adopts a recurrent neural network framework to capture complex temporal and nonlinear dependencies in the data. To our knowledge, G-Net is the first g-computation based deep sequential modeling framework that provides estimates of treatment effects under \em{dynamic} and \em{time-varying} treatment strategies. We evaluate G-Net using simulated longitudinal data from two sources: CVSim, a mechanistic model of the cardiovascular system, and a pharmacokinetic simulation of tumor growth. G-Net outperforms both classical and state-of-the-art counterfactual prediction models in these settings.
APA
Li, R., Hu, S., Lu, M., Utsumi, Y., Chakraborty, P., Sow, D.M., Madan, P., Li, J., Ghalwash, M., Shahn, Z. & Lehman, L.. (2021). G-Net: a Recurrent Network Approach to G-Computation for Counterfactual Prediction Under a Dynamic Treatment Regime. Proceedings of Machine Learning for Health, in Proceedings of Machine Learning Research 158:282-299 Available from https://proceedings.mlr.press/v158/li21a.html.

Related Material