NoteChat: A Dataset of Synthetic Doctor-Patient Conversations Conditioned on Clinical Notes
This addresses the need for better clinical documentation to reduce physician burnout, though it is incremental as it builds on existing LLM methods.
The paper tackles the problem of generating synthetic doctor-patient conversations from clinical notes by introducing NoteChat, a multi-agent LLM framework, and shows it outperforms state-of-the-art models like ChatGPT and GPT-4 by up to 22.78% in evaluations.
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.