Medical-Event-Data-Standard/meds_testing_helpers

View on GitHub

Testing, benchmarking, and synthetic data generation helpers for MEDS tools, pipelines, and models.

Stars: 4
Forks: 0
Open beginner issues: 0
Indexed issues: 15

Dominant language: Python
License: MIT
Last GitHub push: Nov 17, 2025
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: help wanted
PR merge metrics: No merged PRs in 30d

Beginner friendly Everything

Open All

15 open issues indexed

Consider adding a grammar-based synthetic-dataset generator for end-to-end content-correctness testing Open

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#40 · Opened Apr 17, 2026
Should separate the MEDS testing helpers and dataset class utilities from the generation utilities. Open

Code Cleanliness / Technical Debt Generation priority:medium Usability

Difficulty 5/5 Over a week Newbie friendliness 15/100

Medical-Event-Data-Standard/meds_testing_helpers#35 · Opened May 6, 2025
Should be able to import static datasets into other static datasets to avoid static data duplication Open

priority:low Static Datasets

Difficulty 5/5 Over a week Newbie friendliness 30/100

Medical-Event-Data-Standard/meds_testing_helpers#26 · Opened Mar 15, 2025
The `MEDSDataset` Class should be made more helpful in validating prospective MEDS datasets are fully compliant. Open

priority:high Usability

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#25 · Opened Mar 6, 2025
We should explore (and ideally add) more full-featured benchmarking helper functions for MEDS pipelines Open

Benchmarking Utilities priority:high Usability

Difficulty 5/5 Over a week Newbie friendliness 20/100

Medical-Event-Data-Standard/meds_testing_helpers#24 · Opened Mar 3, 2025
The Static Simple Dataset should be updated to better reflect the MEDS standard Open

MEDS Data priority:high Static Datasets

Difficulty 3/5 1-2 days Newbie friendliness 48/100

Medical-Event-Data-Standard/meds_testing_helpers#23 · Opened Mar 3, 2025
We should add meaningful dataset generation templates for MIMIC, eICU, and AUMCdb like datasets Open

Benchmarking Utilities Generation priority:medium

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#22 · Opened Mar 3, 2025
We should use mixture distributions where appropriate rather than categorical Open

enhancement Generation Inference of Generation Configs priority:high

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#21 · Opened Mar 3, 2025
Inferred dataset properites need to be "sanitized" to ensure privacy safety w.r.t. source data Open

bug Inference of Generation Configs priority:critical

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#20 · Opened Mar 3, 2025
Generation and serialization of dataset generative process RVs should happen through a unified class infrastructure in `rvs.py` Open

Code Cleanliness / Technical Debt enhancement Generation Inference of Generation Configs priority:medium

Difficulty 5/5 Over a week Newbie friendliness 25/100

Medical-Event-Data-Standard/meds_testing_helpers#19 · Opened Mar 3, 2025
Need to support use-cases with label dataframes as well Open

enhancement Generation Label DFs priority:high PyTest Fixtures Static Datasets

Difficulty 5/5 Over a week Newbie friendliness 30/100

Medical-Event-Data-Standard/meds_testing_helpers#18 · Opened Mar 3, 2025
We should be able to generate datasets with task labels as well. Open

enhancement Generation Label DFs priority:medium

Difficulty 4/5 3-5 days Newbie friendliness 38/100

Medical-Event-Data-Standard/meds_testing_helpers#11 · Opened Mar 2, 2025
Dataset infernece and generation pipeline needs to be re-worked for fidelity, configuration file exportability, and privacy. Open

bug enhancement Label DFs MEDS Data priority:high Testing (internal)

Difficulty 5/5 Over a week Newbie friendliness 20/100

Medical-Event-Data-Standard/meds_testing_helpers#5 · Opened Feb 28, 2025
We should export hypothesis-library generator functions for property-based testing over MEDS datasets. Open

Generation priority:low Testing (external) Utilities

Difficulty 3/5 1-2 days Newbie friendliness 48/100

Medical-Event-Data-Standard/meds_testing_helpers#4 · 1 comment · Opened Jan 9, 2025
Release 0.5 Open

help wanted priority:high

Difficulty 5/5 Over a week Newbie friendliness 20/100

Medical-Event-Data-Standard/meds_testing_helpers#1 · 1 comment · Opened Jan 7, 2025

Medical-Event-Data-Standard/meds_testing_helpers

Get new issues in your inbox