Medical-Event-Data-Standard / Medical-Event-Data-Standard/MEDS-DEV

We should support evaluation-only mode for pre-trained models distributed with weights

Open
#204 0 comments 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement Experimental API help wanted Models priority:medium Usability/Interface
Dominant language
Python
Stars
43
Forks
10
PR merge metrics
No merged PRs in 30d

Description

Though this should not be the main focus of the benchmark, there is no reason it wouldn't work to just define a model with a predict step and no train step. This would be especially important as we add more of the stanford style models and the EHR Shot dataset (#203) which are more aligned with this approach.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by locating how benchmark models currently define and invoke training and prediction, then review the evaluation path for pre-trained models with weights. Compare the requirements for the Stanford-style models and EHR Shot dataset in issue #203; done means a model can run evaluation with a predict step and no train step.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.