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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wang, Junda, Yao, Zonghai, Yang, Zhichao, Zhou, Huixue, Li, Rumeng, Wang, Xun, Xu, Yucheng, Yu, Hong
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915126549938176
author Wang, Junda
Yao, Zonghai
Yang, Zhichao
Zhou, Huixue
Li, Rumeng
Wang, Xun
Xu, Yucheng
Yu, Hong
author_facet Wang, Junda
Yao, Zonghai
Yang, Zhichao
Zhou, Huixue
Li, Rumeng
Wang, Xun
Xu, Yucheng
Yu, Hong
contents We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues. NoteChat embodies the principle that an ensemble of role-specific LLMs, through structured role-play and strategic prompting, can perform their assigned roles more effectively. The synergy among these role-playing LLMs results in a cohesive and efficient dialogue generation. Evaluation on MTS-dialogue, a benchmark dataset for patient-physician dialogues-note pairs, shows that models trained with the augmented synthetic patient-physician dialogues by NoteChat outperforms other state-of-the-art models for generating clinical notes. Our comprehensive automatic and human evaluation demonstrates that NoteChat substantially surpasses state-of-the-art models like ChatGPT and GPT-4 up to 22.78% by domain experts in generating superior synthetic patient-physician dialogues based on clinical notes. NoteChat has the potential to engage patients directly and help clinical documentation, a leading cause of physician burnout.
format Preprint
id arxiv_https___arxiv_org_abs_2310_15959
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
Wang, Junda
Yao, Zonghai
Yang, Zhichao
Zhou, Huixue
Li, Rumeng
Wang, Xun
Xu, Yucheng
Yu, Hong
Computation and Language
We introduce NoteChat, a novel cooperative multi-agent framework leveraging Large Language Models (LLMs) to generate patient-physician dialogues. NoteChat embodies the principle that an ensemble of role-specific LLMs, through structured role-play and strategic prompting, can perform their assigned roles more effectively. The synergy among these role-playing LLMs results in a cohesive and efficient dialogue generation. Evaluation on MTS-dialogue, a benchmark dataset for patient-physician dialogues-note pairs, shows that models trained with the augmented synthetic patient-physician dialogues by NoteChat outperforms other state-of-the-art models for generating clinical notes. Our comprehensive automatic and human evaluation demonstrates that NoteChat substantially surpasses state-of-the-art models like ChatGPT and GPT-4 up to 22.78% by domain experts in generating superior synthetic patient-physician dialogues based on clinical notes. NoteChat has the potential to engage patients directly and help clinical documentation, a leading cause of physician burnout.
title NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
topic Computation and Language
url https://arxiv.org/abs/2310.15959