Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations

By Ioana Bica, Ahmed M. Alaa, James Jordon, Mihaela van der Schaar. 2020

241 citations recorded by the source corpus.

Identifying when to give treatments to patients and how to select among multiple treatments over time are important medical problems with a few existing solutions. In this paper, we introduce the Counterfactual Recurrent Network (CRN), a novel sequence-to-sequence model that leverages the increasingly available patient observational data to estimate treatment effects over time and answer such medical questions. To handle the bias from time-varying confounders, covariates affecting the treatment assignment policy in the observational data, CRN uses domain adversarial training to build balancing representations of the patient history. At each timestep, CRN constructs a treatment invariant representation which removes the association between patient history and treatment assignments and thus can be reliably used for making counterfactual predictions. On a simulated model of tumour growth, with varying degree of time-dependent confounding, we show how our model achieves lower error in estimating counterfactuals and in choosing the correct treatment and timing of treatment than current state-of-the-art methods.

Subfields: Artificial Intelligence, Statistics and Probability, Representation & Self-Supervised Learning, Causal Inference & Discovery

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Statistics and Probability

In Representation & Self-Supervised Learning

In Causal Inference & Discovery

Citations in the corpus

How artificial intelligence and machine learning can help healthcare systems respond to COVID-19 (2020, background): “In light of the vast heterogeneity of patient characteristics and outcomes (Alaa et al. 2020), blanket hypothesis tests about the disease may appear erroneously inconclusive.”
Causal machine learning for predicting treatment outcomes (2024, unknown): “To address this issue, ML needs to be embedded in a causal framework.”
Estimating the Effects of Continuous-valued Interventions using Generative Adversarial Networks (2020, background): “Moreover, another important research direction is to extend this work to the temporal causal inference setting [26–29] and estimate counterfactual outcomes for sequences of continuous interventions.”
Attentive State-Space Modeling of Disease Progression (2019, background): “Models that are both highly accurate and capable of extracting knowledge from data are important for informing practice guidelines and identifying the patients’ needs and interactions with health services [3, 4, 5, 6].”
Counterfactual Credit Assignment in Model-Free Reinforcement Learning (2020, background): “Also closely related to our paper, Bica et al. (2020) also leverages a similar mechanism to compute counterfactuals, for a different purpose than ours (computing treatment effects vs. policy improvement operators).”
From Real‐World Patient Data to Individualized Treatment Effects Using Machine Learning: Current and Future Methods to Address Underlying Challenges (2020, unknown): “Alternatively, Bica et al .”