AIPatient: Simulating Patients with EHRs and LLM Powered Agentic Workflow

Simulated patient systems play a crucial role in modern medical education and research, providing safe, integrative learning environments and enabling clinical decision-making simulations. Large Language Models (LLM) could advance simulated patient systems by replicating medical conditions and patie...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2024-09
Main Authors: Yu, Huizi, Zhou, Jiayan, Li, Lingyao, Chen, Shan, Gallifant, Jack, Shi, Anye, Li, Xiang, Hua, Wenyue, Jin, Mingyu, Chen, Guang, Zhou, Yang, Zhao, Li, Gupte, Trisha, Ming-Li, Chen, Azizi, Zahra, Zhang, Yongfeng, Assimes, Themistocles L, Ma, Xin, Bitterman, Danielle S, Lu, Lin, Fan, Lizhou
Format: Article
Language:English
Subjects:
Education
Electronic health records
Knowledge bases (artificial intelligence)
Knowledge representation
Large language models
Medical education
Medical research
Reasoning
Retrieval
System effectiveness
Variance analysis
Workflow
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Simulated patient systems play a crucial role in modern medical education and research, providing safe, integrative learning environments and enabling clinical decision-making simulations. Large Language Models (LLM) could advance simulated patient systems by replicating medical conditions and patient-doctor interactions with high fidelity and low cost. However, ensuring the effectiveness and trustworthiness of these systems remains a challenge, as they require a large, diverse, and precise patient knowledgebase, along with a robust and stable knowledge diffusion to users. Here, we developed AIPatient, an advanced simulated patient system with AIPatient Knowledge Graph (AIPatient KG) as the input and the Reasoning Retrieval-Augmented Generation (Reasoning RAG) agentic workflow as the generation backbone. AIPatient KG samples data from Electronic Health Records (EHRs) in the Medical Information Mart for Intensive Care (MIMIC)-III database, producing a clinically diverse and relevant cohort of 1,495 patients with high knowledgebase validity (F1 0.89). Reasoning RAG leverages six LLM powered agents spanning tasks including retrieval, KG query generation, abstraction, checker, rewrite, and summarization. This agentic framework reaches an overall accuracy of 94.15% in EHR-based medical Question Answering (QA), outperforming benchmarks that use either no agent or only partial agent integration. Our system also presents high readability (median Flesch Reading Ease 77.23; median Flesch Kincaid Grade 5.6), robustness (ANOVA F-value 0.6126, p
ISSN:2331-8422