inspect ./work/bcauss
Learning End-to-End Patient Representations through Self-Supervised Covariate Balancing for Causal Treatment Effect Estimation
Self-supervised covariate balancing
- Date
- Role
- Coauthor
- Type
- publication
- Source
- PubMed journal record and public BCAUSS repository, reviewed 2026-10-27
This research introduces BCAUSS, a multi-task neural approach that combines outcome prediction with a self-supervised covariate-balancing objective for causal treatment-effect estimation.
The paper was published in the Journal of Biomedical Informatics in 2023. The public citation lists Gino Tesei, Stefanos Giampanis, Jingpu Shi, and Beau Norgeot as authors.