This repository contains source code for paper "Estimating Individual Treatment Effects with Time-Varying Confounders".

In this paper, we study the problem of Estimating individual treatment effects with time-varying confounders (as illustrated by a causal graph in the figure below)

We propose Deep Sequential Weighting (DSW) for estimating ITE with time-varying confounders. DSW consists of three main components: representation learning module, balancing module and prediction module.

To demonstrate the effectiveness of our framework, we conduct comprehensive experiments on synthetic, semi-synthetic and real-world EMR datasets (MIMIC-III). DSW outperforms state-of-the-art baselines in terms of PEHE and ATE.

Ubuntu16.04, python 3.6

Install pytorch 1.4

Simulate the all covariates, treatments and outcomes

cd simulation
python synthetic.py

With a similar simulation process, we construct a semi-synthetic dataset based on a real-world dataset: MIMIC-III.

cd simulation
python synthetic_mimic.py

Obtain the patients data of two treatment-outcome pairs: (1) vasopressor-Meanbp; (2) ventilator-SpO2.

cd simulation
python pre_mimic.py

We show the full list of static demographics and time-varying covariates of sepsis patients obtained from MIMIC-III.

python train_synthetic.py --observation_window 30 --epochs 64 --batch-size 128 --lr 1e-3

• ITE estimation metrics: PEHE, ATE
• Factual prediction metric: RMSE