Inverse Probability of Treatment Weighting with Deep Sequence Models Enables Accurate treatment effect Estimation from Electronic Health Records

TL;DR

This paper introduces a method using deep sequence models to directly estimate propensity scores from electronic health records, enabling unbiased treatment effect estimation despite time-dependent confounding.

Contribution

It demonstrates that deep sequence models can accurately estimate propensity scores for IPTW without feature engineering, improving treatment effect estimation from longitudinal EHR data.

Findings

Deep models outperform traditional feature-based methods in propensity score estimation.

Accurate treatment effect estimates achieved with synthetic and semi-synthetic datasets.

Method reduces reliance on domain knowledge and feature engineering.

Abstract

Observational data have been actively used to estimate treatment effect, driven by the growing availability of electronic health records (EHRs). However, EHRs typically consist of longitudinal records, often introducing time-dependent confoundings that hinder the unbiased estimation of treatment effect. Inverse probability of treatment weighting (IPTW) is a widely used propensity score method since it provides unbiased treatment effect estimation and its derivation is straightforward. In this study, we aim to utilize IPTW to estimate treatment effect in the presence of time-dependent confounding using claims records. Previous studies have utilized propensity score methods with features derived from claims records through feature processing, which generally requires domain knowledge and additional resources to extract information to accurately estimate propensity scores. Deep sequence models, particularly recurrent neural networks and self-attention-based architectures, have demonstrated good performance in modeling EHRs for various downstream tasks. We propose that these deep sequence models can provide accurate IPTW estimation of treatment effect by directly estimating the propensity scores from claims records without the need for feature processing. We empirically demonstrate this by conducting comprehensive evaluations using synthetic and semi-synthetic datasets.