EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Personalized Treatment Effect Estimation from Observational EHR with Causal Representation Learning

Frank Harris

American Journal of Data Science and Analysis · 31.12.2025 · 6 (4) · 103-115

DOI: 10.71465/ajdsa3465 ↗

Kurz gefasst

Fachartikel in der Zeitschrift American Journal of Data Science and Analysis, online erschienen am 31.12.2025. Verfasst von Frank Harris. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread adoption of Electronic Health Records (EHR) has generated massive repositories of longitudinal patient data, offering unprecedented opportunities for data-driven healthcare and precision medicine. A central challenge in this domain is the estimation of Personalized Treatment Effects (PTE), which aims to predict the individual-level response to specific medical interventions. Unlike prediction tasks in standard supervised learning, PTE estimation is fundamentally a causal inference problem characterized by the absence of counterfactual outcomes in the training data. Furthermore, observational EHR data is plagued by selection bias, where treatment assignments are correlated with patient characteristics, leading to confounding. In this paper, we propose a novel deep learning framework for estimating PTE from high-dimensional, sparse, and irregular EHR data. Our approach leverages Causal Representation Learning to project patient covariates into a latent space where the distribution of control and treated populations is balanced, thereby mitigating selection bias. We introduce a disentangled representation architecture that separates instrumental factors, confounding factors, and adjustment factors, ensuring that the learned representations retain predictive power for the outcome while satisfying the ignorability assumption. We validate our method on both semi-synthetic datasets and real-world clinical cohorts derived from critical care databases. The experimental results demonstrate that our approach significantly outperforms state-of-the-art baselines in estimating heterogeneous treatment effects, providing a robust tool for clinical decision support.

Zitieren

APA

Harris, F. (2025). Personalized Treatment Effect Estimation from Observational EHR with Causal Representation Learning. American Journal of Data Science and Analysis, 6(4), 103-115. https://doi.org/10.71465/ajdsa3465

Vancouver

Harris F. Personalized Treatment Effect Estimation from Observational EHR with Causal Representation Learning. American Journal of Data Science and Analysis. 2025;6(4):103-115. doi:10.71465/ajdsa3465

BibTeX
@article{Harris2025,
  author = {Harris, Frank},
  title = {Personalized Treatment Effect Estimation from Observational EHR with Causal Representation Learning},
  journal = {American Journal of Data Science and Analysis},
  year = {2025},
  volume = {6},
  number = {4},
  pages = {103--115},
  doi = {10.71465/ajdsa3465}
}
Kostenlos starten →