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

You might also read

Related Articles

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

Sort by
Same author

A minimally invasive robotic spinal surgical system for anterior lumbar nerve decompression.

Science robotics·2026
Same author

Locus-Specific Convergent Evolution and Interchromosomal Rearrangements Contribute to the Diversification of Amniote Type I Interferons.

Evolutionary applications·2026
Same author

Grounding large language models in clinical diagnostics.

Nature communications·2026
Same author

Reliability of Large Language Model Generated Clinical Reasoning in Assisted Reproductive Technology: Blinded Comparative Evaluation Study.

Journal of medical Internet research·2026
Same author

Dual-Camera Markerless Motion Capture System for Precise Lower-Limb Kinematic Analysis in Osteoarthritis.

Annals of biomedical engineering·2025
Same author

Diffusion Model-Based Multi-Channel EEG Representation and Forecasting for Early Epileptic Seizure Warning.

Interdisciplinary sciences, computational life sciences·2025

Related Experiment Video

Updated: Jun 4, 2025

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

498

Application of Large Language Models in Medical Training Evaluation-Using ChatGPT as a Standardized Patient:

Chenxu Wang1,2,3, Shuhan Li1,2, Nuoxi Lin1,2

  • 1West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China.

Journal of Medical Internet Research
|January 1, 2025
PubMed
Summary
This summary is machine-generated.

Large language models like ChatGPT can effectively simulate standardized patients for medical history-taking tasks. Prompt engineering significantly enhances ChatGPT's accuracy and realism for medical education.

Keywords:
ChatGPTaccuracyartificial intelligencehealth careinflammatory bowel diseaselarge language modelsmedical trainingperformance evaluationprompt engineeringstandardized patient

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
13:44

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques

Published on: December 9, 2022

3.4K

Related Experiment Videos

Last Updated: Jun 4, 2025

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

498
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques
13:44

Project-Based Learning Guidelines for Health Sciences Students: An Analysis with Data Mining and Qualitative Techniques

Published on: December 9, 2022

3.4K

Area of Science:

  • Medical Education Technology
  • Artificial Intelligence in Healthcare
  • Natural Language Processing

Background:

  • Growing interest in applying large language models (LLMs) in medicine.
  • Limited evaluation of LLMs as standardized patients for medical assessments.
  • Exploring ChatGPT as a cost-effective alternative for history-taking training.

Purpose of the Study:

  • Assess ChatGPT's viability and performance as a standardized patient.
  • Utilize prompt engineering to enhance accuracy in medical assessments.
  • Evaluate ChatGPT's role in transforming medical education.

Main Methods:

  • Two-phase experiment: feasibility and performance evaluation.
  • Simulated history-taking conversations (IBD) with varying inquiry quality.
  • Assessed anthropomorphism, clinical accuracy, and adaptability using prompt refinement.
  • Compared performance with original and revised prompts across 300+ runs.
  • Tested generalizability with other scripts and explored language impact.

Main Results:

  • ChatGPT effectively simulated standardized patients, differentiating inquiry qualities.
  • Revised prompts significantly improved realism and accuracy (4.9x improvement).
  • Score difference percentage dropped from 29.83% to 6.06% with revised prompts.
  • Performance on separate scripts was acceptable (3.21% difference).
  • Language variations did not significantly impact chatbot performance.

Conclusions:

  • ChatGPT is a viable tool for simulating standardized patients in medical assessments.
  • Prompt engineering substantially enhances scoring accuracy and response realism.
  • LLMs like ChatGPT show potential for improving medical training and clinical readiness.