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

Targeted Cancer Therapies02:57

Targeted Cancer Therapies

7.4K
The targeted cancer therapies, also known as “molecular targeted therapies,” take advantage of the molecular and genetic differences between the cancer cells and the normal cells. It needs a thorough understanding of the cancer cells to develop drugs that can target specific molecular aspects that drive the growth, progression, and spread of cancer cells without affecting the growth and survival of other normal cells in the body.
There are several types of targeted therapies against...
7.4K

You might also read

Related Articles

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

Sort by
Same author

A Large Language Model-Powered Multiagent Framework Emulating Standardized Patients in Clinical Communication Skills Training: Development and Evaluation Study.

Journal of medical Internet research·2026
Same author

Low vitamin D and folate levels are associated with costochondritis: a retrospective cross-sectional study on children with impaired bone health.

BMC pediatrics·2026
Same author

Large Language Model-Enhanced Drug Repositioning Knowledge Extraction via Long Chain-of-Thought: Development and Evaluation Study.

JMIR medical informatics·2025
Same author

Predicting Waiting Times for Medical Tasks in a Pediatric Hospital Using Machine Learning: Comprehensive, Retrospective, Real-World Study.

JMIR medical informatics·2025
Same author

Enhancing early gestational diabetes mellitus prediction with imputation-based machine learning framework: A comparative study on real-world clinical records.

Digital health·2025
Same author

A Module-Level Polygenic Risk Score-Based NetWAS Framework for Identifying AD Genetic Modules Mediated by Amygdala: An ADNI Study.

International journal of molecular sciences·2025

Related Experiment Video

Updated: May 21, 2025

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

2.3K

Prompt Framework for Extracting Scale-Related Knowledge Entities from Chinese Medical Literature: Development and

Jie Hao1, Zhenli Chen1, Qinglong Peng2,3

  • 1Institute of Medical Information/Medical Library, Chinese Academy of Medical Sciences & Peking Union Medical College, Beijing, China.

Journal of Medical Internet Research
|March 18, 2025
PubMed
Summary

MedScaleNER enhances large language model (LLM) performance for extracting medical scale entities from Chinese texts. This framework improves knowledge discovery, supporting measurement-based care implementation.

Keywords:
AIChinaChinese medical literatureLLMMBCMedScaleNERartificial intelligencedatasetframeworkin-context learninginformation retrievallarge language modelmeasurement-based caremedical literaturenamed entity recognitionpromptprompt engineeringprompt frameworkretrievalscale

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K
Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease
08:15

Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease

Published on: May 10, 2024

480

Related Experiment Videos

Last Updated: May 21, 2025

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

2.3K
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.7K
Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease
08:15

Author Spotlight: Network Pharmacology and Molecular Docking to Decipher the Action of Jiawei Shengjiang San Against Diabetic Kidney Disease

Published on: May 10, 2024

480

Area of Science:

  • Natural Language Processing (NLP)
  • Medical Informatics
  • Artificial Intelligence

Background:

  • Measurement-based care improves patient outcomes but faces adoption barriers due to limited structured knowledge in Chinese medical literature.
  • Extracting medical scale-related knowledge entities is challenging due to unstructured text and scarce annotated data.
  • Large Language Models (LLMs) show potential for Named Entity Recognition (NER), but specialized prompting is crucial for medical scales in low-resource settings.

Purpose of the Study:

  • To develop and evaluate MedScaleNER, a task-oriented prompt framework for optimizing LLM performance in recognizing medical scale-related entities.
  • To address the challenges of extracting knowledge from unstructured Chinese medical literature.
  • To enhance the accuracy of NER for medical scales in low-resource environments.

Main Methods:

  • MedScaleNER utilizes demonstration retrieval, chain-of-thought prompting, and self-verification for improved NER performance.
  • A k-nearest neighbors approach dynamically retrieves optimal examples for in-context learning.
  • The NER task is decomposed into entity type identification and labeling, with self-verification ensuring output reliability.

Main Results:

  • The CMedS-NER dataset comprises 720 papers with 27,499 annotated scale-related entities.
  • MedScaleNER, using GLM-4-0520, achieved a macro F1-score of 59.64% for scale-related entities.
  • In low-resource settings (1% data), MedScaleNER outperformed locally fine-tuned models, demonstrating the effectiveness of demonstration retrieval and self-verification.

Conclusions:

  • MedScaleNER advances LLM applications and prompt engineering for specialized NER in Chinese medical literature.
  • The framework facilitates efficient and reliable knowledge extraction from unstructured texts with limited data.
  • MedScaleNER supports broader measurement-based care implementation, improving clinical and research outcomes.