Dual-agent approach improves synthetic medical consultation dialogues
Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation
Computation and LanguageArtificial IntelligenceMachine Learning
Summary
Collecting realistic medical conversations before doctor visits is hard because of privacy concerns. The authors created a system where two AI agents—one acting as the patient with a specific persona, and one as the doctor following clinical guidelines—talk to each other. This method produces synthetic medical dialogues that better mimic real doctor-patient interactions, covering important medical details and sounding natural. The synthetic data can then help train other medical dialogue tools.
What this means in practice
- •For medical chatbot developers: Generate realistic synthetic pre-consultation dialogues to train and improve chatbot performance in patient interviewing.
- •For clinical training teams: Create varied practice dialogues that reflect realistic patient diversity and clinical protocols for trainee doctors.
Authors
Qiyuan Li, Xiaomei Guo, Chao Gao, Haijiang Liu, Deyu Chen, Caicai Guo, Jinguang Gu
Abstract
Pre-consultation medical dialogues are essential for collecting comprehensive patient information, but are costly to obtain at scale due to privacy and ethical constraints. Existing LLM-based synthesis methods often rely on prompt engineering or rigid rules, limiting their ability to balance clinical relevance with realistic patient diversity. We propose CoRPS-Dial, a controllable dual-agent framework for pre-consultation medical dialogue synthesis that integrates patient personas with guideline-aligned clinical workflow rules. CoRPS-Dial generates dialogues through interactions between a persona-driven patient agent and a process-guided doctor agent, followed by post-hoc quality control for role consistency, workflow completeness, and textual consistency. Experiments on coronary heart disease demonstrate that CoRPS-Dial improves alignment between synthetic and real dialogues in information coverage, clinical compliance, and dialogue naturalness. Downstream fine-tuning experiments further confirm the utility of the generated synthetic data for medical dialogue tasks. These results highlight the effectiveness of CoRPS-Dial for clinically grounded and controllable medical dialogue synthesis.