Synthetic or Authentic? Building Mental Patient Simulators from Longitudinal Evidence

TL;DR

This paper introduces DEPROFILE, a novel framework for creating realistic mental health patient simulators by integrating diverse longitudinal data, significantly improving dialogue quality and behavioral diversity in simulations.

Contribution

The paper presents DEPROFILE, a new data-grounded patient simulation framework that leverages longitudinal evidence to enhance realism and coherence in mental health dialogue systems.

Findings

Enhanced dialogue realism and diversity with DEPROFILE

Improved simulation coherence using longitudinal data

Outperforms state-of-the-art baselines in multiple metrics

Abstract

Patient simulation is essential for developing and evaluating mental health dialogue systems. As most existing approaches rely on snapshot-style prompts with limited profile information, homogeneous behaviors and incoherent disease progression in multi-turn interactions have become key chellenges. In this work, we propose DEPROFILE, a data-grounded patient simulation framework that constructs unified, multi-source patient profiles by integrating demographic attributes, standardized clinical symptoms, counseling dialogues, and longitudinal life-event histories from real-world data. We further introduce a Chain-of-Change agent to transform noisy longitudinal records into structured, temporally grounded memory representations for simulation. Experiments across multiple large language model (LLM) backbones show that with more comprehensive profile constructed by DEPROFILE, the dialogue realism, behavioral diversity, and event richness have consistently improved and exceed state-of-the-art baselines, highlighting the importance of grounding patient simulation in verifiable longitudinal evidence.