Skip to content

[help-wanted-dev] TSTR benchmark via SynthEHRella #26

Description

@ArioMoniri

Use the standardized SynthEHRella framework: 80/20 split of source by HASTA_ID, train syntha on the 80%, generate same-size synthetic, train HTN-risk model on each, score on the held-out 20% real. Report ROC-AUC, Brier, calibration plot. Goal: TSTR within 0.02 ROC-AUC of TRTR. Output goes to benchmarks/results/.json regenerated each release.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    help-wanted-devNeeds a Python / TypeScript / Rust developer.

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions