SynthAgent: A Multi-Agent LLM Framework for Realistic Patient Simulation -- A Case Study in Obesity with Mental Health Comorbidities
This provides a scalable and privacy-preserving tool for medical and psychological research to explore patient journeys and behavioral dynamics, though it is incremental as it applies existing multi-agent and LLM methods to a specific domain.
The study tackled the problem of simulating high-fidelity patients for complex diseases like obesity with mental health comorbidities by introducing SynthAgent, a multi-agent LLM framework, and found that GPT-5 and Claude 4.5 Sonnet achieved the highest fidelity in evaluations of over 100 generated patients.
Simulating high-fidelity patients offers a powerful avenue for studying complex diseases while addressing the challenges of fragmented, biased, and privacy-restricted real-world data. In this study, we introduce SynthAgent, a novel Multi-Agent System (MAS) framework designed to model obesity patients with comorbid mental disorders, including depression, anxiety, social phobia, and binge eating disorder. SynthAgent integrates clinical and medical evidence from claims data, population surveys, and patient-centered literature to construct personalized virtual patients enriched with personality traits that influence adherence, emotion regulation, and lifestyle behaviors. Through autonomous agent interactions, the system simulates disease progression, treatment response, and life management across diverse psychosocial contexts. Evaluation of more than 100 generated patients demonstrated that GPT-5 and Claude 4.5 Sonnet achieved the highest fidelity as the core engine in the proposed MAS framework, outperforming Gemini 2.5 Pro and DeepSeek-R1. SynthAgent thus provides a scalable and privacy-preserving framework for exploring patient journeys, behavioral dynamics, and decision-making processes in both medical and psychological domains.