NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes. Wang, J., Yao, Z., Yang, Z., Zhou, H., Li, R., Wang, X., Xu, Y., & Yu, H. October, 2023. Number: arXiv:2310.15959 arXiv:2310.15959 [cs]![NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex The detailed clinical records drafted by doctors after each patient's visit are crucial for medical practitioners and researchers. Automating the creation of these notes with language models can reduce the workload of doctors. However, training such models can be difficult due to the limited public availability of conversations between patients and doctors. In this paper, we introduce NoteChat, a cooperative multi-agent framework leveraging Large Language Models (LLMs) for generating synthetic doctor-patient conversations conditioned on clinical notes. NoteChat consists of Planning, Roleplay, and Polish modules. We provide a comprehensive automatic and human evaluation of NoteChat, comparing it with state-of-the-art models, including OpenAI's ChatGPT and GPT-4. Results demonstrate that NoteChat facilitates high-quality synthetic doctor-patient conversations, underscoring the untapped potential of LLMs in healthcare. This work represents the first instance of multiple LLMs cooperating to complete a doctor-patient conversation conditioned on clinical notes, offering promising avenues for the intersection of AI and healthcare
@misc{wang_notechat_2023,
title = {{NoteChat}: {A} {Dataset} of {Synthetic} {Doctor}-{Patient} {Conversations} {Conditioned} on {Clinical} {Notes}},
shorttitle = {{NoteChat}},
url = {http://arxiv.org/abs/2310.15959},
abstract = {The detailed clinical records drafted by doctors after each patient's visit are crucial for medical practitioners and researchers. Automating the creation of these notes with language models can reduce the workload of doctors. However, training such models can be difficult due to the limited public availability of conversations between patients and doctors. In this paper, we introduce NoteChat, a cooperative multi-agent framework leveraging Large Language Models (LLMs) for generating synthetic doctor-patient conversations conditioned on clinical notes. NoteChat consists of Planning, Roleplay, and Polish modules. We provide a comprehensive automatic and human evaluation of NoteChat, comparing it with state-of-the-art models, including OpenAI's ChatGPT and GPT-4. Results demonstrate that NoteChat facilitates high-quality synthetic doctor-patient conversations, underscoring the untapped potential of LLMs in healthcare. This work represents the first instance of multiple LLMs cooperating to complete a doctor-patient conversation conditioned on clinical notes, offering promising avenues for the intersection of AI and healthcare},
urldate = {2023-11-15},
publisher = {arXiv},
author = {Wang, Junda and Yao, Zonghai and Yang, Zhichao and Zhou, Huixue and Li, Rumeng and Wang, Xun and Xu, Yucheng and Yu, Hong},
month = oct,
year = {2023},
note = {Number: arXiv:2310.15959
arXiv:2310.15959 [cs]},
keywords = {Computer Science - Computation and Language},
}
Downloads: 0
{"_id":"9ThXdcunWAf44Dbs7","bibbaseid":"wang-yao-yang-zhou-li-wang-xu-yu-notechatadatasetofsyntheticdoctorpatientconversationsconditionedonclinicalnotes-2023","author_short":["Wang, J.","Yao, Z.","Yang, Z.","Zhou, H.","Li, R.","Wang, X.","Xu, Y.","Yu, H."],"bibdata":{"bibtype":"misc","type":"misc","title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","shorttitle":"NoteChat","url":"http://arxiv.org/abs/2310.15959","abstract":"The detailed clinical records drafted by doctors after each patient's visit are crucial for medical practitioners and researchers. Automating the creation of these notes with language models can reduce the workload of doctors. However, training such models can be difficult due to the limited public availability of conversations between patients and doctors. In this paper, we introduce NoteChat, a cooperative multi-agent framework leveraging Large Language Models (LLMs) for generating synthetic doctor-patient conversations conditioned on clinical notes. NoteChat consists of Planning, Roleplay, and Polish modules. We provide a comprehensive automatic and human evaluation of NoteChat, comparing it with state-of-the-art models, including OpenAI's ChatGPT and GPT-4. Results demonstrate that NoteChat facilitates high-quality synthetic doctor-patient conversations, underscoring the untapped potential of LLMs in healthcare. This work represents the first instance of multiple LLMs cooperating to complete a doctor-patient conversation conditioned on clinical notes, offering promising avenues for the intersection of AI and healthcare","urldate":"2023-11-15","publisher":"arXiv","author":[{"propositions":[],"lastnames":["Wang"],"firstnames":["Junda"],"suffixes":[]},{"propositions":[],"lastnames":["Yao"],"firstnames":["Zonghai"],"suffixes":[]},{"propositions":[],"lastnames":["Yang"],"firstnames":["Zhichao"],"suffixes":[]},{"propositions":[],"lastnames":["Zhou"],"firstnames":["Huixue"],"suffixes":[]},{"propositions":[],"lastnames":["Li"],"firstnames":["Rumeng"],"suffixes":[]},{"propositions":[],"lastnames":["Wang"],"firstnames":["Xun"],"suffixes":[]},{"propositions":[],"lastnames":["Xu"],"firstnames":["Yucheng"],"suffixes":[]},{"propositions":[],"lastnames":["Yu"],"firstnames":["Hong"],"suffixes":[]}],"month":"October","year":"2023","note":"Number: arXiv:2310.15959 arXiv:2310.15959 [cs]","keywords":"Computer Science - Computation and Language","bibtex":"@misc{wang_notechat_2023,\n\ttitle = {{NoteChat}: {A} {Dataset} of {Synthetic} {Doctor}-{Patient} {Conversations} {Conditioned} on {Clinical} {Notes}},\n\tshorttitle = {{NoteChat}},\n\turl = {http://arxiv.org/abs/2310.15959},\n\tabstract = {The detailed clinical records drafted by doctors after each patient's visit are crucial for medical practitioners and researchers. Automating the creation of these notes with language models can reduce the workload of doctors. However, training such models can be difficult due to the limited public availability of conversations between patients and doctors. In this paper, we introduce NoteChat, a cooperative multi-agent framework leveraging Large Language Models (LLMs) for generating synthetic doctor-patient conversations conditioned on clinical notes. NoteChat consists of Planning, Roleplay, and Polish modules. We provide a comprehensive automatic and human evaluation of NoteChat, comparing it with state-of-the-art models, including OpenAI's ChatGPT and GPT-4. Results demonstrate that NoteChat facilitates high-quality synthetic doctor-patient conversations, underscoring the untapped potential of LLMs in healthcare. This work represents the first instance of multiple LLMs cooperating to complete a doctor-patient conversation conditioned on clinical notes, offering promising avenues for the intersection of AI and healthcare},\n\turldate = {2023-11-15},\n\tpublisher = {arXiv},\n\tauthor = {Wang, Junda and Yao, Zonghai and Yang, Zhichao and Zhou, Huixue and Li, Rumeng and Wang, Xun and Xu, Yucheng and Yu, Hong},\n\tmonth = oct,\n\tyear = {2023},\n\tnote = {Number: arXiv:2310.15959\narXiv:2310.15959 [cs]},\n\tkeywords = {Computer Science - Computation and Language},\n}\n\n","author_short":["Wang, J.","Yao, Z.","Yang, Z.","Zhou, H.","Li, R.","Wang, X.","Xu, Y.","Yu, H."],"key":"wang_notechat_2023","id":"wang_notechat_2023","bibbaseid":"wang-yao-yang-zhou-li-wang-xu-yu-notechatadatasetofsyntheticdoctorpatientconversationsconditionedonclinicalnotes-2023","role":"author","urls":{"Paper":"http://arxiv.org/abs/2310.15959"},"keyword":["Computer Science - Computation and Language"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"misc","biburl":"http://fenway.cs.uml.edu/papers/pubs-all.bib","dataSources":["TqaA9miSB65nRfS5H"],"keywords":["computer science - computation and language"],"search_terms":["notechat","dataset","synthetic","doctor","patient","conversations","conditioned","clinical","notes","wang","yao","yang","zhou","li","wang","xu","yu"],"title":"NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes","year":2023}