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

TL;DR

SynDocDis is a new framework that uses structured prompts and de-identified metadata to generate realistic physician discussions, addressing privacy concerns and filling a gap in synthetic medical dialogue generation.

Contribution

It introduces a novel approach combining structured prompting with privacy-preserving metadata to synthesize physician-to-physician dialogues for medical AI applications.

Findings

Physicians rated communication effectiveness at 4.4/5.

Medical content quality scored 4.1/5.

Achieved 91% clinical relevance with strong privacy preservation.

Abstract

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 regulations and ethical considerations severely restrict access to such data. While synthetic data generation using Large Language Models offers a promising alternative, existing approaches primarily focus on patient-physician interactions or structured medical records, leaving a significant gap in physician-to-physician communication synthesis. We present SynDocDis, a novel framework that combines structured prompting techniques with privacy-preserving de-identified case metadata to generate clinically accurate physician-to-physician dialogues. Evaluation by five practicing physicians in nine oncology and hepatology scenarios demonstrated exceptional communication effectiveness (mean 4.4/5) and strong medical content quality (mean 4.1/5), with substantial interrater reliability (kappa = 0.70, 95% CI: 0.67-0.73). The framework achieved 91% clinical relevance ratings while maintaining doctors' and patients' privacy. These results place SynDocDis as a promising framework for advancing medical AI research ethically and responsibly through privacy-compliant synthetic physician dialogue generation with direct applications in medical education and clinical decision support.