AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data

• URL: http://arxiv.org/abs/2506.04032v1
• Date: Wed, 04 Jun 2025 14:56:08 GMT
• Title: AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data
• Authors: Sina Rashidian, Nan Li, Jonathan Amar, Jong Ha Lee, Sam Pugh, Eric Yang, Geoff Masterson, Myoung Cha, Yugang Jia, Akhil Vaid,
• Abstract summary: We present a Patient Simulator that leverages real world patient encounters.<n>The simulator provides a realistic approach to patient presentation and multi-turn conversation with a symptom-checking agent.
• Score: 3.4206930658402115
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Background: We present a Patient Simulator that leverages real world patient encounters which cover a broad range of conditions and symptoms to provide synthetic test subjects for development and testing of healthcare agentic models. The simulator provides a realistic approach to patient presentation and multi-turn conversation with a symptom-checking agent. Objectives: (1) To construct and instantiate a Patient Simulator to train and test an AI health agent, based on patient vignettes derived from real EHR data. (2) To test the validity and alignment of the simulated encounters provided by the Patient Simulator to expert human clinical providers. (3) To illustrate the evaluation framework of such an LLM system on the generated realistic, data-driven simulations -- yielding a preliminary assessment of our proposed system. Methods: We first constructed realistic clinical scenarios by deriving patient vignettes from real-world EHR encounters. These vignettes cover a variety of presenting symptoms and underlying conditions. We then evaluate the performance of the Patient Simulator as a simulacrum of a real patient encounter across over 500 different patient vignettes. We leveraged a separate AI agent to provide multi-turn questions to obtain a history of present illness. The resulting multiturn conversations were evaluated by two expert clinicians. Results: Clinicians scored the Patient Simulator as consistent with the patient vignettes in those same 97.7% of cases. The extracted case summary based on the conversation history was 99% relevant. Conclusions: We developed a methodology to incorporate vignettes derived from real healthcare patient data to build a simulation of patient responses to symptom checking agents. The performance and alignment of this Patient Simulator could be used to train and test a multi-turn conversational AI agent at scale.

Related papers

• PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions [15.272979678875787]
  We introduce PatientSim, a patient simulator that generates realistic and diverse patient personas for clinical scenarios.<n>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.<n>The top-performing open-source model, Llama 3.3, was validated by four clinicians to confirm the robustness of our framework.
  arXiv  Detail & Related papers  (2025-05-23T12:34:48Z)
• MIL vs. Aggregation: Evaluating Patient-Level Survival Prediction Strategies Using Graph-Based Learning [52.231128973251124]
  We compare various strategies for predicting survival at the WSI and patient level.<n>The former treats each WSI as an independent sample, mimicking the strategy adopted in other works.<n>The latter comprises methods to either aggregate the predictions of the several WSIs or automatically identify the most relevant slide.
  arXiv  Detail & Related papers  (2025-03-29T11:14:02Z)
• Self-Evolving Multi-Agent Simulations for Realistic Clinical Interactions [16.50490537786593]
  We introduce MedAgentSim, an open-source simulated clinical environment with doctor, patient, and measurement agents.<n>Unlike prior approaches, our framework requires doctor agents to actively engage with patients through multi-turn conversations.<n>We incorporate self improvement mechanisms that allow models to iteratively refine their diagnostic strategies.
  arXiv  Detail & Related papers  (2025-03-28T17:59:53Z)
• Exploring the Inquiry-Diagnosis Relationship with Advanced Patient Simulators [5.217925404425509]
  This paper extracts dialogue strategies from real doctor-patient conversations to guide the training of a patient simulator.<n>Our simulator shows higher anthropomorphism and lower hallucination rates, using dynamic dialogue strategies.
  arXiv  Detail & Related papers  (2025-01-16T11:41:14Z)
• LLMs Can Simulate Standardized Patients via Agent Coevolution [8.539733225671059]
  Training medical personnel using standardized patients (SPs) remains a complex challenge.<n>EvoPatient is a novel simulated patient framework in which a patient agent and doctor agents simulate the diagnostic process through multi-turn dialogues.<n>Our framework improves over existing reasoning methods by more than 10% in requirement alignment and better human preference.
  arXiv  Detail & Related papers  (2024-12-16T12:36:47Z)
• Dr-LLaVA: Visual Instruction Tuning with Symbolic Clinical Grounding [53.629132242389716]
  Vision-Language Models (VLM) can support clinicians by analyzing medical images and engaging in natural language interactions. VLMs often exhibit "hallucinogenic" behavior, generating textual outputs not grounded in contextual multimodal information. We propose a new alignment algorithm that uses symbolic representations of clinical reasoning to ground VLMs in medical knowledge.
  arXiv  Detail & Related papers  (2024-05-29T23:19:28Z)
• AI Hospital: Benchmarking Large Language Models in a Multi-agent Medical Interaction Simulator [69.51568871044454]
  We introduce textbfAI Hospital, a framework simulating dynamic medical interactions between emphDoctor as player and NPCs. This setup allows for realistic assessments of LLMs in clinical scenarios. We develop the Multi-View Medical Evaluation benchmark, utilizing high-quality Chinese medical records and NPCs.
  arXiv  Detail & Related papers  (2024-02-15T06:46:48Z)
• TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
  Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
  arXiv  Detail & Related papers  (2023-07-19T12:35:09Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• SmartTriage: A system for personalized patient data capture, documentation generation, and decision support [9.09817311390571]
  We developed a machine-learning-backed system, SmartTriage, which goes beyond conventional symptom checking through a tight bi-directional integration with the electronic medical record (EMR) SmartTriage identifies the patient's chief complaint from a free-text entry and then asks a series of discrete questions to obtain relevant symptomatology. The patient-specific data are used to predict detailed ICD-10-CM codes as well as medication, laboratory, and imaging orders.
  arXiv  Detail & Related papers  (2020-10-19T22:45:27Z)
• Hemogram Data as a Tool for Decision-making in COVID-19 Management: Applications to Resource Scarcity Scenarios [62.997667081978825]
  COVID-19 pandemics has challenged emergency response systems worldwide, with widespread reports of essential services breakdown and collapse of health care structure. This work describes a machine learning model derived from hemogram exam data performed in symptomatic patients. Proposed models can predict COVID-19 qRT-PCR results in symptomatic individuals with high accuracy, sensitivity and specificity.
  arXiv  Detail & Related papers  (2020-05-10T01:45:03Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.