PatientSim：一個基於人物角色的模擬器，用於實現真實的醫患互動

摘要

醫患諮詢需要多輪次、情境感知的溝通，並針對不同的患者角色進行定制。在這樣的環境中訓練或評估醫生大型語言模型（LLM）需要真實的患者互動系統。然而，現有的模擬器往往無法反映臨床實踐中見到的多樣化患者角色。為解決這一問題，我們引入了PatientSim，這是一個基於醫學專業知識生成真實且多樣化患者角色的患者模擬器，適用於臨床場景。PatientSim的運作基於：1）從MIMIC-ED和MIMIC-IV數據集的真實世界數據中提取的臨床檔案，包括症狀和病史；以及2）由四個維度定義的角色：性格、語言能力、病史回憶水平和認知混亂程度，共產生37種獨特組合。我們評估了八種LLM的事實準確性和角色一致性。表現最佳的開源模型Llama 3.3經過四位臨床醫生的驗證，確認了我們框架的穩健性。作為一個開源、可定制的平台，PatientSim提供了一個可重現且可擴展的解決方案，能夠根據具體的培訓需求進行定制。它提供了一個符合隱私保護的環境，作為評估醫療對話系統在多樣化患者表現下的穩健測試平台，並展現了作為醫療教育工具的潛力。

English

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 evaluated eight LLMs for factual accuracy and persona consistency. The top-performing open-source model, Llama 3.3, was 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.

PatientSim：一個基於人物角色的模擬器，用於實現真實的醫患互動

PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions

摘要

Summary

Support

Support