paper-with-me

홈 › Papers

Synthetic Patient-Physician Dialogue Generation from Clinical Notes Using LLM

2024-08-12 · Trisha Das, Dina Albassam, Jimeng Sun

Medical dialogue systems (MDS) enhance patient-physician communication, improve healthcare accessibility, and reduce costs. However, acquiring suitable data to train these systems poses significant challenges. Privacy concerns prevent the use of real conversations, necessitating synthetic alternatives. Synthetic dialogue generation from publicly available clinical notes offers a promising solution to this issue, providing realistic data while safeguarding privacy. Our approach, SynDial, uses a single LLM iteratively with zero-shot prompting and a feedback loop to generate and refine high-quality synthetic dialogues. The feedback consists of weighted evaluation scores for similarity and extractiveness. The iterative process ensures dialogues meet predefined thresholds, achieving superior extractiveness as a result of the feedback loop. Additionally, evaluation shows that the generated dialogues excel in factuality metric compared to the baselines and has comparable diversity scores with GPT4.

📄 PDF Abstract BibTeX arXiv:2408.06285

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue GenerationDiversity

Similar Papers 제목 키워드 기반

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

2023-10-24 · Junda Wang, Zonghai Yao, Zhichao Yang, Huixue Zhou 외

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, th…

Dialogue Generation

SynDocDis: A Metadata-Driven Framework for Generating Synthetic Physician Discussions Using Large Language Models

2026-03-16 · Beny Rubinstein, Sergio Matos arxiv

Physician-physician discussions of patient cases represent a rich source of clinical knowledge and reasoning that could feed AI agents to enrich and even participate in subsequent interactions. However, privacy regulatio…

Synthetic Data GenerationDialogue GenerationClinical Knowledge

Doctorina MedBench: A Dialogue-Based Benchmark and Evaluation Framework for Agent-Based Medical AI

2026-03-26 · Anna Kozlova, Stanislau Salavei, Pavel Satalkin, Hanna Plotnitskaya 외 arxiv

We present Doctorina MedBench, an evaluation framework for agent-based medical AI based on the simulation of physician-patient interactions. Unlike traditional medical benchmarks that rely on solving standardized test qu…

Semi-Supervised Variational Reasoning for Medical Dialogue Generation

2021-05-13 · Dongdong Li, Zhaochun Ren, Pengjie Ren, Zhumin Chen 외

Medical dialogue generation aims to provide automatic and accurate responses to assist physicians to obtain diagnosis and treatment suggestions in an efficient manner. In medical dialogues two key characteristics are rel…

Dialogue GenerationResponse Generation

Using Medical Algorithms for Task-Oriented Dialogue in LLM-Based Medical Interviews

2025-10-14 · Rui Reis, Pedro Rangel Henriques, João Ferreira-Coimbra, Eva Oliveira 외 arxiv

We developed a task-oriented dialogue framework structured as a Directed Acyclic Graph (DAG) of medical questions. The system integrates: (1) a systematic pipeline for transforming medical algorithms and guidelines into …