Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Issues And Trends In Healthcare Delivery System01:29

Issues And Trends In Healthcare Delivery System

6.5K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
6.5K
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

333
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
333

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same authorSame journal

Motivation and perceived learning in serious games: Reflexive thematic analysis of educational escape room experiences.

Medical teacher·2026
Same author

Using Generative AI to Appraise the Quality of Medical Education Research Studies: Agreement Between AI-Generated and Human MERSQI Scores.

AEM education and training·2026
Same author

Artificial Intelligence to Support Qualitative Data Analysis: Promises, Approaches, Pitfalls.

Academic medicine : journal of the Association of American Medical Colleges·2025
Same author

Global research aims for the study of cost and value in health professions education: A Delphi study of international experts.

Medical teacher·2025
Same author

Curriculum Research Solutions: Shifting From "Did It Work Locally?" to Contributing to a Scholarly Conversation.

Academic medicine : journal of the Association of American Medical Colleges·2025
Same author

Virtual Patients Using Large Language Models: Scalable, Contextualized Simulation of Clinician-Patient Dialogue With Feedback.

Journal of medical Internet research·2025

Related Experiment Video

Updated: May 5, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

3.9K

Creating virtual patients using large language models: scalable, global, and low cost.

David A Cook1

  • 1Mayo Multidisciplinary Simulation Center, Mayo Clinic College of Medicine and Science, Rochester, MN, USA.

Medical Teacher
|July 12, 2024
PubMed
Summary

Artificial intelligence (AI) large language models (LLMs) enable the creation of low-cost virtual patients (VPs) for scalable medical education. This disruptive innovation offers global accessibility, revolutionizing clinical reasoning training and assessment.

Keywords:
Simulation Trainingartificial intelligenceclinical decision-makingclinical reasoningcomputer-assisted instruction

More Related Videos

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

3.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Related Experiment Videos

Last Updated: May 5, 2026

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data
09:34

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

3.9K
Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
09:15

Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training

Published on: February 10, 2022

3.4K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Area of Science:

  • Medical Education Technology
  • Artificial Intelligence in Healthcare
  • Clinical Reasoning Simulation

Background:

  • Virtual patients (VPs) are valuable tools for teaching and assessing clinical reasoning but are often limited by high costs and implementation challenges.
  • Existing VP platforms require significant financial investment and logistical planning, hindering widespread adoption.
  • There is a need for more accessible and scalable solutions to deliver effective clinical reasoning training globally.

Purpose of the Study:

  • To describe a novel, low-cost, and scalable approach for developing virtual patients using artificial intelligence (AI) large language models (LLMs).
  • To demonstrate the feasibility of creating interactive VPs with varying contextual features using prompt engineering and LLMs.
  • To explore the potential of LLM-based VPs to democratize medical education and assessment worldwide.

Main Methods:

  • Leveraged OpenAI's Generative Pretrained Transformer (GPT) models (GPT-3.5-turbo and GPT-4.0) to create and implement interactive virtual patients.
  • Employed systematic prompt engineering to instruct ChatGPT in emulating patient scenarios and providing clinician performance feedback.
  • Developed a text-only interface via the OpenAI API for VP interaction and conducted comparative testing between GPT-4.0 and Anthropic Claude.

Main Results:

  • GPT-4.0 demonstrated superior performance in creating and managing virtual patient interactions compared to GPT-3.5-turbo.
  • The developed LLM-VPs were found to be substantially more accessible due to low cost and ease of implementation.
  • Limited testing with Anthropic Claude showed promising results, indicating potential for broader LLM application.

Conclusions:

  • LLM-based virtual patients represent a disruptive innovation, offering unprecedented accessibility and scalability in medical education.
  • This approach can democratize the development and use of educational and clinical simulations globally.
  • LLM-VPs have the potential to revolutionize the teaching, assessment, and research of clinical reasoning, shared decision-making, and AI evaluation.