https://github.com/som-shahlab/medalign

MedAlign is a clinician-generated dataset for instruction following with electronic medical records.
https://github.com/som-shahlab/medalign

Last synced: about 1 month ago
JSON representation

MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

• Host: GitHub
• URL: https://github.com/som-shahlab/medalign
• Owner: som-shahlab
• License: mit
• Created: 2023-08-31T17:32:02.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-10-19T19:48:03.000Z (about 1 year ago)
• Last Synced: 2024-08-02T19:37:00.894Z (4 months ago)
• Size: 316 KB
• Stars: 85
• Watchers: 21
• Forks: 9
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

• awesome-latest-LLM - MedAlign(Stanford)

README

        
# MedAlign

MedAlign is a clinician-generated dataset for instruction following with electronic medical records.

The MedAlign dataset contains:

- 1314 clinician-generated instructions, 983 after removing duplicates using ROUGE-L overlap;

- 276 longitudinal EHRs;

- 303 clinician-generated responses to instruction-EHR pairs.

All data assets will be shared in coming months, under a standard research license and data use agreement (similar to the PhysioNet Credentialed Health [Data License](https://physionet.org/content/mimiciv/view-license/2.2/) and [Data Use Agreement](https://physionet.org/content/mimiciv/view-dua/2.2/), which require users to undergo [CITI training](https://physionet.org/content/mimiciv/view-required-training/2.2/) prior to access).

For more information, please visit [our website](https://medalign.stanford.edu) or read the main MedAlign [paper](https://arxiv.org/abs/2012.07421).

For questions and feedback, please post on the [discussion board](https://github.com/som-shahlab/medalign/discussions).