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

ER Retrieval Pathway01:45

ER Retrieval Pathway

4.0K
In the secretory pathway, vesicles transport proteins from one cellular compartment to another in forward transport to deliver the protein to its correct location. Occasionally, misfolded proteins and incorrect proteins escape their original compartments, and a retrieval pathway is used to return the escaped proteins to their original compartment.
The ER uses many checkpoints to prevent the entry of incorrectly folded or a resident protein as cargo onto a transport vesicle. These mechanisms...
4.0K

You might also read

Related Articles

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

Sort by
Same author

DispFormer: A dual attention transformer with denoising for biomedical irregular time series classification.

Journal of biomedical informatics·2026
Same author

A temporal deep learning algorithm for prediction of extubation failures in critical care patients.

Journal of clinical monitoring and computing·2026
Same author

DynaMamba: Multi-scale dynamic interacting Mamba network for irregular clinical time series classification.

Journal of biomedical informatics·2026
Same author

Contextual information contributes to biomedical named entity normalization.

Journal of biomedical informatics·2025
Same author

Self-Supervised Molecular Representation Learning With Topology and Geometry.

IEEE journal of biomedical and health informatics·2024
Same author

Revisiting Drug Recommendation From a Causal Perspective.

IEEE journal of biomedical and health informatics·2024

Related Experiment Video

Updated: Oct 2, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

644

Leveraging Multi-source knowledge for Chinese clinical named entity recognition via relational graph convolutional

Ying Xiong1, Hao Peng2, Yang Xiang3

  • 1Department of Computer Science, Harbin Institute of Technology, Shenzhen, China; Peng Cheng Laboratory, Shenzhen, China.

Journal of Biomedical Informatics
|February 26, 2022
PubMed
Summary

This study introduces MKRGCN, a novel method that unifies Chinese Clinical Named Entity Recognition (CNER) by integrating multi-source external knowledge. The model effectively combines lexicon and knowledge graph information, significantly improving CNER performance.

Keywords:
Clinical named entity recognitionGraph neural networkMulti-source knowledge

More Related Videos

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

Related Experiment Videos

Last Updated: Oct 2, 2025

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
05:47

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

644
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

538

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Bioinformatics

Background:

  • External knowledge sources like lexicons and knowledge graphs enhance Named Entity Recognition (NER).
  • Existing methods often use single knowledge sources or treat them independently.
  • Integrating multi-source knowledge with boundary information is crucial for Chinese Clinical NER (CNER).

Purpose of the Study:

  • To propose a novel method, MKRGCN, for Chinese Clinical NER (CNER) that unifies multi-source external knowledge.
  • To effectively combine lexicon words and knowledge graph concepts with their boundaries for improved CNER.
  • To leverage relational graph convolutional networks (RGCN) for modeling multi-source knowledge.

Main Methods:

  • Developed MKRGCN, a method based on RGCN to integrate multi-source knowledge for CNER.
  • Constructed relational graphs linking lexicon words/KG concepts to sentence tokens, incorporating boundary information.
  • Integrated knowledge-enhanced token representations with context representations using an attention mechanism.
  • Employed a conditional random field (CRF) layer for final named entity label prediction.

Main Results:

  • Achieved state-of-the-art performance on CCKS2017 and CCKS2018 datasets for Chinese CNER, with F1-scores of 91.88% and 89.91%, respectively.
  • Significantly outperformed existing methods in Chinese CNER tasks.
  • Demonstrated the method's effectiveness on English datasets (NCBI-Disease, BC2GM) even with a single knowledge source.

Conclusions:

  • The MKRGCN model effectively integrates knowledge from external lexicons and knowledge graphs for Chinese CNER.
  • The proposed approach shows potential for application in English NER tasks.
  • Unified multi-source knowledge integration offers a promising direction for advancing NER systems.