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

<i>Morinda officinalis</i> oligosaccharides ameliorate corticosterone‑induced depression‑like behaviour in mice by modulating the BDNF signalling pathway and gut microbiota.

Molecular medicine reports·2026
Same author

Quantitative mapping of prefrontal oxygenation dysfunction and neuropsychiatric symptoms in patients with systemic lupus erythematosus: a multichannel functional near-infrared spectroscopy study.

Lupus science & medicine·2026
Same author

Autonomous Motion Vision with Tri-bulk-heterojunctioned Organic Adaptation Transistor.

Nature communications·2026
Same author

Influence of sex and systemic lupus erythematosus disease status on cerebral cortex structure.

Lupus science & medicine·2026
Same author

Mechanisms and effects of ozone-pullulanase treatment on multiscale structures and in vitro digestibility of rice starch.

Food chemistry·2026
Same author

Multisource attribution and transfer dynamics of PTEs in soil-rice systems in Southwestern China.

Scientific reports·2026

Related Experiment Video

Updated: May 17, 2025

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

33.6K

Psychomedical named entity recognition method based on multi-level feature extraction and multi-granularity embedding

Zixuan Liu1, Guofang Zhang2, Yanguang Shen3

  • 1School of Cyber Security and Computer, Hebei University, Baoding, 071000, China.

Scientific Reports
|May 15, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces a novel Named Entity Recognition (NER) method for psychomedicine, enhancing accuracy by fusing multi-level features. The MFME-NER model significantly improves entity recognition in complex psychological texts.

Keywords:
GA-FNNAttention mechanismMFE-BERT modelMulti-granularity fusionNamed entity recognitionPsychological medicine

More Related Videos

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.5K

Related Experiment Videos

Last Updated: May 17, 2025

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

33.6K
Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding
11:25

Simultaneous Scalp Electroencephalography EEG, Electromyography EMG, and Whole-body Segmental Inertial Recording for Multi-modal Neural Decoding

Published on: July 26, 2013

43.2K
Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology
09:44

Author Spotlight: Advancing Large-Scale Neural Dynamics Through HD-MEA Technology

Published on: March 8, 2024

4.5K

Area of Science:

  • Natural Language Processing
  • Computational Linguistics
  • Psychomedicine Informatics

Background:

  • Psychomedicine texts present unique challenges for Named Entity Recognition (NER) due to long paragraphs, complex sentences, and scattered knowledge.
  • Existing character-based NER models lack structural and phonetic information, limiting their effectiveness in the psychomedical domain.
  • Migrating general-domain NER models to psychomedicine does not sufficiently improve entity recognition accuracy.

Purpose of the Study:

  • To propose an innovative Named Entity Recognition (NER) method for psychomedicine, named MFME-NER (multi-level feature extraction and multi-granularity embedding fusion).
  • To enhance the semantic representation of psychomedical texts by incorporating multi-granularity embedding information.
  • To improve the accuracy of entity recognition in specialized psychomedical texts.

Main Methods:

  • Introduced three embedding granularities: character, radical, and pinyin, to enrich text representation.
  • Developed a multi-layer feature extraction BERT (MFE-BERT) model for pre-training character embeddings.
  • Utilized BiLSTM for character-level features and CNN for radical and pinyin features, followed by feature fusion using a gated feed-forward neural network attention mechanism (GA-FNNAtention).

Main Results:

  • The MFME-NER method achieved a 94.26% F1 Score on the self-constructed PsyDatase dataset.
  • The method obtained an 89.63% F1 Score on the CBLUE dataset.
  • The proposed method demonstrated superior performance compared to existing evaluation metrics, confirming its efficacy.

Conclusions:

  • The MFME-NER method offers an effective solution for Named Entity Recognition in psychomedicine.
  • The integration of multi-level features and multi-granularity embeddings significantly boosts entity recognition accuracy.
  • This approach provides a valuable tool for the analysis of complex psychomedical data.