Skip to content

This is a fork of the work done in ACI Bench that will be used as the basis for benchmarks to be used on work being done as part of the applied research here with ClinicianFOCUS.

Notifications You must be signed in to change notification settings

ClinicianFOCUS/cf-aci-bench

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ACI-BENCH

Introduction

This repository contains the data and source code for:

Aci-bench: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation". Wen-wai Yim, Yujuan Fu, Asma Ben Abacha, Neal Snider, Thomas Lin, Meliha Yetisgen. Submitted to Nature Scientific Data, 2023. https://www.nature.com/articles/s41597-023-02487-3

@article{aci-bench,
  author = {Wen{-}wai Yim and
                Yujuan Fu and
                Asma {Ben Abacha} and
                Neal Snider and Thomas Lin and Meliha Yetisgen},
  title = {ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation},
  journal = {Nature Scientific Data},
  year = {2023}
}

Data statistics

The ACI-BENCH collection consists of full doctor-patient conversations and associated clinical notes and includes the data splits from the MEDIQA-CHAT 2023 and MEDIQA-SUM 2023 challenges:

TRAIN: 67
VALID: 20
TEST1: 40 ( MEDIQA-CHAT TASK B test set )
TEST2: 40 ( MEDIQA-CHAT TASK C test set )
TEST3: 40 ( MEDIQA-SUM TASK C test set )

License

The data here is published under a Creative Commons Attribution 4.0 International Licence (CC BY). https://creativecommons.org/licenses/by/4.0/

Contact

-  Asma Ben abacha (abenabacha at microsoft dot com)
 - Wen-wai Yim (yimwenwai at microsoft dot com)

About

This is a fork of the work done in ACI Bench that will be used as the basis for benchmarks to be used on work being done as part of the applied research here with ClinicianFOCUS.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 54.0%
  • Jupyter Notebook 39.5%
  • Shell 6.5%