Causal Machine Learning Framework for Adjusting Treatment Switching in Clinical Trials

1.1 MB of research materials proposing a causal machine-learning framework to adjust for post-randomization treatment switching in randomized trials. The work includes comprehensive simulation studies and a real-data application, authored by Yi Liu and last updated in April 2026. The materials are available as PDF and TXT files under a CC-BY-4.0 license.

Use Cases

• Developing causal ML methods for the no-switch estimand based on the described framework.
• Simulating treatment-switching scenarios based on the described comprehensive simulation studies.
• Applying transfer-learning–based reweighting techniques based on the proposed bias-correction approach.
• Predicting counterfactual outcomes for switching patients based on the described three-step framework.
• Extending adjustment methods to multi-arm trials based on the described natural extension.

Strengths

• Includes a real-data application demonstrating practical performance.
• Framework is designed to handle multi-directional switching and multi-arm trials.
• Materials are openly licensed under CC-BY-4.0.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is small (1.1 MB), likely containing methodological documentation rather than large-scale trial data.

Provenance

Source

figshare, authored by Yi Liu.

Collection Method

Likely contains research paper and supplementary materials describing the proposed methodological framework.

Time Range

null

Freshness

Last updated 2026-04-13 12:39:40; freshness should be verified.

Geography

null