Medical-Event-Data-Standard / Medical-Event-Data-Standard/MEDS-DEV
We need to add a more robust initial cohort of models and improve issues with existing models
Open
Nobody has claimed this yet.
Models
priority:medium
- Dominant language
- Python
- Stars
- 43
- Forks
- 10
- PR merge metrics
- No merged PRs in 30d
Description
These initial models include:
- A generative, autoregressive foundation model (current candidate: ETHOS; alternates include ESGPT analog models).
- A non-autoregressive, SOTA foundation model (current candidate: MOTOR)
- A contrastive model (current candidate: EBCL)
- Improved baseline models (improve performance of included meds-tab models)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the existing MEDS-DEV model implementations and the included meds-tab baselines, then compare the proposed candidates: ETHOS or ESGPT analog models, MOTOR, and EBCL. Clarify the expected evaluation and integration criteria before work begins. Done means adding the requested model cohort and improving the baseline models' performance, with reproducible comparisons.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100