UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?

Junda Wang, Zonghai Yao, Avijit Mitra, Samuel Osebe, Zhichao Yang +1 more
6/29/2023
cs.CLcs.AI

No official code found. Best implementation: believewhat/Dr.NoteAid (16 stars, last commit 2024-01-03).

Abstract

This paper presents UMASS_BioNLP team participation in the MEDIQA-Chat 2023 shared task for Task-A and Task-C. We focus especially on Task-C and propose a novel LLMs cooperation system named a doctor-patient loop to generate high-quality conversation data sets. The experiment results demonstrate that our approaches yield reasonable performance as evaluated by automatic metrics such as ROUGE, medical concept recall, BLEU, and Self-BLEU. Furthermore, we conducted a comparative analysis between our proposed method and ChatGPT and GPT-4. This analysis also investigates the potential of utilizing cooperation LLMs to generate high-quality datasets.

View on arXivView PDF

Code Implementations(1)

believewhat/Dr.NoteAidCommunity100%

ACL Workshop 2023

167PythonMar 23, 20232 years ago

Similar Papers

WangLab at MEDIQA-Chat 2023: Clinical Note Generation from Doctor-Patient Conversations using Large Language Models

84% match2023

ACI-BENCH: a Novel Ambient Clinical Intelligence Dataset for Benchmarking Automatic Visit Note Generation

83% match2023

NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes

83% match1 repo162023

DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation

82% match1 repo5662023

SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulation

81% match2 repos2026

Synthetic Patient-Physician Dialogue Generation from Clinical Notes Using LLM

81% match2024

Cite this paper

@article{wang2023umassbionlp,
  title  = {UMASS_BioNLP at MEDIQA-Chat 2023: Can LLMs generate high-quality synthetic note-oriented doctor-patient conversations?},
  author = {Junda Wang and Zonghai Yao and Avijit Mitra and Samuel Osebe and Zhichao Yang and Hong Yu},
  year   = {2023},
  eprint = {2306.16931},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.16931v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.16931.svg)](https://codeofpaper.com/paper/2306.16931)

Discussion