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

Development and Interpretability Analysis of a Stacking Ensemble Model for Early Prediction of Nutritional Risk in Intensive Care Unit Patients: Retrospective Cohort Study.

JMIR medical informatics·2026
Same author

Evaluating ChatGPT's Adherence to Medical Ethics: A Prerequisite for Artificial Intelligence in Medicine.

Health care science·2026
Same author

Interpretable Machine Learning Model for Predicting and Assessing the Risk of Diabetic Nephropathy: Prediction Model Study.

JMIR medical informatics·2025
Same author

Characterizing pituitary adenomas in clinical notes: Corpus construction and its application in LLMs.

Health informatics journal·2024
Same author

Correction: A Multilabel Text Classifier of Cancer Literature at the Publication Level: Methods Study of Medical Text Classification.

JMIR medical informatics·2024
Same author

Potential Target Discovery and Drug Repurposing for Coronaviruses: Study Involving a Knowledge Graph-Based Approach.

Journal of medical Internet research·2023

Related Experiment Video

Updated: Jul 31, 2025

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

16.0K

Chinese Clinical Named Entity Recognition From Electronic Medical Records Based on Multisemantic Features by Using

Weijie Wang1, Xiaoying Li1, Huiling Ren1

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

JMIR Medical Informatics
|May 10, 2023
PubMed
Summary

This study introduces a novel Chinese clinical named entity recognition (CNER) method using multisemantic features to improve machine understanding of electronic medical records (EMRs). The approach significantly enhances CNER accuracy, aiding medical research and decision-making.

Keywords:
CNNChinese clinical named entity recognitionRoBERTa-wwmRobustly Optimized Bidirectional Encoder Representation from Transformers Pretraining Approach Whole Word Maskingconvolutional neural networkimage featuremultisemantic features

More Related Videos

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

641
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

2.6K

Related Experiment Videos

Last Updated: Jul 31, 2025

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

16.0K
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

641
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

2.6K

Area of Science:

  • Natural Language Processing
  • Medical Informatics
  • Machine Learning

Background:

  • Clinical electronic medical records (EMRs) contain vital patient data but are challenging to mine due to complex Chinese grammar.
  • Accurate Chinese clinical named entity recognition (CNER) is crucial for downstream tasks like knowledge graph construction and medical decision support.
  • Existing CNER methods struggle with the nuances of Chinese medical text, necessitating advanced approaches.

Purpose of the Study:

  • To develop a Chinese CNER method that learns semantics-enriched representations from electronic medical records (EMRs).
  • To enhance machine comprehension of deep semantic information within EMRs by utilizing multisemantic features.
  • To improve the readability and understandability of medical information extracted from EMRs.

Main Methods:

  • Employed Robustly Optimized Bidirectional Encoder Representation from Transformers Pretraining Approach Whole Word Masking (RoBERTa-wwm) with dynamic fusion and Chinese character features (5-stroke, Zheng, phonological, stroke codes) extracted via 1D CNNs.
  • Utilized 2D CNNs to extract Chinese character image features by converting characters into images.
  • Integrated multisemantic features into Bidirectional Long Short-Term Memory with Conditional Random Fields (BiLSTM-CRF) for CNER.

Main Results:

  • Achieved F1-scores of 89.28% on the Yidu-S4K dataset and 84.61% on a self-annotated dataset.
  • The proposed model outperformed baseline and existing research models in CNER tasks.
  • Ablation analysis confirmed that each incorporated feature and method contributed to improved entity recognition ability.

Conclusions:

  • The proposed CNER method effectively mines deep semantic information from EMRs using multisemantic embedding (RoBERTa-wwm, CNNs).
  • Enhanced semantic recognition at various granularity levels and improved generalization capability through information complementarity.
  • The method enables machines to semantically understand EMRs, significantly boosting CNER task accuracy.