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

Pharmacokinetic Models: Comparison and Selection Criterion01:26

Pharmacokinetic Models: Comparison and Selection Criterion

Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.

You might also read

Related Articles

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

Sort by
Same author

Development of a System for Predicting Hospitalization Time for Patients With Traumatic Brain Injury Based on Machine Learning Algorithms: User-Centered Design Case Study.

JMIR human factors·2024
Same author

Combining Clinical-Radiomics Features With Machine Learning Methods for Building Models to Predict Postoperative Recurrence in Patients With Chronic Subdural Hematoma: Retrospective Cohort Study.

Journal of medical Internet research·2024
Same author

Construction of a predictive model based on MIV-SVR for prognosis and length of stay in patients with traumatic brain injury: Retrospective cohort study.

Digital health·2023
Same author

A Machine Learning-Based Approach to Predict Prognosis and Length of Hospital Stay in Adults and Children With Traumatic Brain Injury: Retrospective Cohort Study.

Journal of medical Internet research·2022

Related Experiment Video

Updated: May 11, 2026

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
08:32

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks

Published on: September 5, 2019

5.9K

Multiple Large Language Models' Performance on the Chinese Medical Licensing Examination: Quantitative Comparative

Yanyu Diao1, Mengyuan Wu1, Jingwen Xu1

  • 1The School of Big Data and Artificial Intelligence, Anhui Xinhua University, 555 Wangjiang West Road, Hefei, 230088, China, 86 15905667742.

JMIR Human Factors
|December 16, 2025
PubMed
Summary

GPT-4 and Chinese LLMs like DeepSeek show promise for medical education, performing well on the Chinese National Medical Licensing Examination (NMLE). Further development is needed for complex tasks, but these AI tools can supplement medical training.

Keywords:
AIChatGPTChinese National Medical Licensing ExaminationERNIE BotTongyi Qianwenartificial intelligencemedical student

More Related Videos

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.1K
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

986

Related Experiment Videos

Last Updated: May 11, 2026

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks
08:32

Examining Online Syntactic Processing of Spoken Complex Sentences in Chinese Using Dual-Modal Interference Tasks

Published on: September 5, 2019

5.9K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

3.1K
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

986

Area of Science:

  • Artificial Intelligence in Medical Education
  • Natural Language Processing (NLP) for Healthcare
  • Large Language Models (LLMs) Performance Evaluation

Background:

  • ChatGPT's capabilities are known, but its performance on the Chinese National Medical Licensing Examination (NMLE) and in Chinese medical education is largely unexamined.
  • Emerging Chinese corpus-based large language models (LLMs), including ERNIE Bot, Tongyi Qianwen, Doubao, and DeepSeek, require systematic evaluation for their effectiveness in the NMLE context.

Purpose of the Study:

  • To quantitatively compare the performance of six leading LLMs (GPT-3.5, GPT-4, ERNIE Bot, Tongyi Qianwen, Doubao, and DeepSeek) on NMLE questions from 2018 to 2024.
  • To assess the feasibility of these LLMs as supplementary educational tools within Chinese medical education.

Main Methods:

  • Selection of NMLE General Written test questions from 2018-2024 across four content units.
  • Preprocessing of image- and table-based content into standardized text formats for LLM input.
  • Evaluation of LLM responses based on accuracy, comprehensiveness, and logical coherence, benchmarked against official answer keys and a passing score of 360/600.

Main Results:

  • GPT-4 consistently outperformed GPT-3.5, achieving high accuracy rates across all tested units.
  • Among Chinese LLMs, DeepSeek demonstrated the highest overall performance, with average accuracies significantly exceeding other domestic models and approaching GPT-4's level.
  • GPT-4 (77.0% accuracy) and DeepSeek (75.8% accuracy) both significantly outperformed GPT-3.5 (68.5% accuracy) and exceeded the NMLE passing threshold, indicating their potential utility.

Conclusions:

  • GPT-4 and advanced Chinese LLMs like DeepSeek show significant potential as supplementary tools for Chinese medical education, evidenced by their strong performance on the NMLE.
  • Further advancements are necessary in areas such as complex reasoning, multimodal processing, and dynamic knowledge updates for these AI models.
  • Human medical expertise remains indispensable for clinical practice and education, with AI tools serving as supportive resources rather than replacements.