Accurate treatment effect estimation using inverse probability of treatment weighting with deep learning
JAMIA Open · 06.03.2025 · 8 (2)
DOI: 10.1093/jamiaopen/ooaf032 ↗Kurz gefasst
Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 26.04.2025. Verfasst von Junghwan Lee und 3 weiteren Autor:innen. Beteiligte Einrichtung: H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIDDK NIH HHS, National Institutes of Health.
Abstract (Originalsprache)
Objectives
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 confounding 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. Materials and Methods 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 learning, particularly using deep sequence models such as recurrent neural networks and Transformer, has 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.
Results
Comprehensive evaluations on synthetic and semi-synthetic datasets demonstrate that IPTW treatment effect estimation using deep sequence models consistently outperforms baseline approaches, including logistic regression and multilayer perceptrons, combined with feature processing.
Discussion
Our findings demonstrate that deep sequence models consistently outperform traditional approaches in estimating treatment effects, particularly under time-dependent confounding. Moreover, Transformer-based models offer interpretability by assigning higher attention weights to relevant confounders, even when prior domain knowledge is limited.
Conclusion
Deep sequence models enable accurate treatment effect estimation through IPTW without the need for feature processing.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332, United States.
ORCID-Profile: Junghwan Lee
Förderung
- NIDDK NIH HHS
- National Institutes of Health
Zitieren
APA
Lee, J., Ma, S., Serban, N., & Yang, S. (2025). Accurate treatment effect estimation using inverse probability of treatment weighting with deep learning. JAMIA Open, 8(2). https://doi.org/10.1093/jamiaopen/ooaf032
Vancouver
Lee J, Ma S, Serban N, Yang S. Accurate treatment effect estimation using inverse probability of treatment weighting with deep learning. JAMIA Open. 2025;8(2). doi:10.1093/jamiaopen/ooaf032
BibTeX
@article{Lee2025,
author = {Lee, Junghwan and Ma, Simin and Serban, Nicoleta and Yang, Shihao},
title = {Accurate treatment effect estimation using inverse probability of treatment weighting with deep learning},
journal = {JAMIA Open},
year = {2025},
volume = {8},
number = {2},
doi = {10.1093/jamiaopen/ooaf032}
}
EUVIMED