PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914120437071872 |
|---|---|
| author | Kyung, Daeun Chung, Hyunseung Bae, Seongsu Kim, Jiho Sohn, Jae Ho Kim, Taerim Kim, Soo Kyung Choi, Edward |
| author_facet | Kyung, Daeun Chung, Hyunseung Bae, Seongsu Kim, Jiho Sohn, Jae Ho Kim, Taerim Kim, Soo Kyung Choi, Edward |
| contents | Doctor-patient consultations require multi-turn, context-aware communication tailored to diverse patient personas. Training or evaluating doctor LLMs in such settings requires realistic patient interaction systems. However, existing simulators often fail to reflect the full range of personas seen in clinical practice. To address this, we introduce PatientSim, a patient simulator that generates realistic and diverse patient personas for clinical scenarios, grounded in medical expertise. PatientSim operates using: 1) clinical profiles, including symptoms and medical history, derived from real-world data in the MIMIC-ED and MIMIC-IV datasets, and 2) personas defined by four axes: personality, language proficiency, medical history recall level, and cognitive confusion level, resulting in 37 unique combinations. We evaluate eight LLMs for factual accuracy and persona consistency. The top-performing open-source model, Llama 3.3 70B, is validated by four clinicians to confirm the robustness of our framework. As an open-source, customizable platform, PatientSim provides a reproducible and scalable solution that can be customized for specific training needs. Offering a privacy-compliant environment, it serves as a robust testbed for evaluating medical dialogue systems across diverse patient presentations and shows promise as an educational tool for healthcare. The code is available at https://github.com/dek924/PatientSim. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_17818 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions Kyung, Daeun Chung, Hyunseung Bae, Seongsu Kim, Jiho Sohn, Jae Ho Kim, Taerim Kim, Soo Kyung Choi, Edward Artificial Intelligence Computation and Language Doctor-patient consultations require multi-turn, context-aware communication tailored to diverse patient personas. Training or evaluating doctor LLMs in such settings requires realistic patient interaction systems. However, existing simulators often fail to reflect the full range of personas seen in clinical practice. To address this, we introduce PatientSim, a patient simulator that generates realistic and diverse patient personas for clinical scenarios, grounded in medical expertise. PatientSim operates using: 1) clinical profiles, including symptoms and medical history, derived from real-world data in the MIMIC-ED and MIMIC-IV datasets, and 2) personas defined by four axes: personality, language proficiency, medical history recall level, and cognitive confusion level, resulting in 37 unique combinations. We evaluate eight LLMs for factual accuracy and persona consistency. The top-performing open-source model, Llama 3.3 70B, is validated by four clinicians to confirm the robustness of our framework. As an open-source, customizable platform, PatientSim provides a reproducible and scalable solution that can be customized for specific training needs. Offering a privacy-compliant environment, it serves as a robust testbed for evaluating medical dialogue systems across diverse patient presentations and shows promise as an educational tool for healthcare. The code is available at https://github.com/dek924/PatientSim. |
| title | PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2505.17818 |