Distributional Balancing with Machine Learning for Clinical Trial Augmentation Using Real-World Data

Abstract

In clinical trials, randomization of treatment and control groups is typically used to ensure the groups have similar covariate distributions on average, resulting in unbiased causal effect estimation. Such balanced covariate distributions are hard to achieve in practice, however, due to recruitment costs, patient dropouts, and more. One possible solution to this problem is to include control patients from external, real world databases. In this paper, we propose DBML, a method that selects control units from a real world database by matching the distribution between the treatment group and the potential control group, instead of matching units between two groups. DBML has three steps. First, we detect anomalous database units (with respect to the treatment distribution) using a variational autoencoder. Second, we re-weight the remaining database units to match the distribution of the treatments. Finally, we use these weights to sample units for our control group. The proposed method is compared to alternative matching-based algorithms and weighted algorithms, achieving superior performance in covariate balance.

Weighted Spline-Expanded Networks with Distributional Balancing for Continuous Treatment Effects
Shucheng Liu, Chan Park, Guanhua Chen
arXiv27 Sep 2026PreprintarXiv licenceFull textStatisticsarXiv
Sliced L^p Distributional Balancing
Haoran Zhang, Guanhua Chen, Chan Park
arXiv27 Sep 2026PreprintCC BY-NC-ND 4.0Full textStatisticsarXiv
An explainable machine learning framework for cross-dataset chronic kidney disease risk prediction using hybrid data balancing
Jarin Tasnim Mumu, Ismail Hossain, Kazi Md. Tanvir Anzum
PLOS One5 Nov 2026Peer-reviewedCC BY 4.0Statistics Epidemiology & public healthPLOS
Online Inference in Distributional Temporal-Difference Learning
Yang Peng, Liangyu Zhang
arXiv16 Oct 2026PreprintCC BY 4.0Full textStatisticsarXiv
A Distributional Optimisation Perspective on Combining Models in Deep Learning
Congye Wang, Yan Lin, Zheyang Shen +2
arXiv21 Sep 2026PreprintCC BY 4.0Full textStatisticsarXiv

Cite

BibTeX RIS

BibTeX

@misc{ke2026distributional,
  title = {{Distributional Balancing with Machine Learning for Clinical Trial Augmentation Using Real-World Data}},
  author = {Zern Ke and Mingshi Cui and Gemma Moran and Javier Cabrera},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.23524},
  eprint = {2609.23524},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.23524},
}

RIS

TY  - UNPB
TI  - Distributional Balancing with Machine Learning for Clinical Trial Augmentation Using Real-World Data
AU  - Zern Ke
AU  - Mingshi Cui
AU  - Gemma Moran
AU  - Javier Cabrera
PY  - 2026
DA  - 2026/09/20
PB  - arXiv
DO  - 10.48550/arxiv.2609.23524
UR  - https://arxiv.org/abs/2609.23524
AB  - In clinical trials, randomization of treatment and control groups is typically used to ensure the groups have similar covariate distributions on average, resulting in unbiased causal effect estimation. Such balanced covariate distributions are hard to achieve in practice, however, due to recruitment costs, patient dropouts, and more. One possible solution to this problem is to include control patients from external, real world databases. In this paper, we propose DBML, a method that selects control units from a real world database by matching the distribution between the treatment group and the potential control group, instead of matching units between two groups. DBML has three steps. First, we detect anomalous database units (with respect to the treatment distribution) using a variational autoencoder. Second, we re-weight the remaining database units to match the distribution of the treatments. Finally, we use these weights to sample units for our control group. The proposed method is compared to alternative matching-based algorithms and weighted algorithms, achieving superior performance in covariate balance.
ER  -

Abstract

Related

Cite