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 Experiment Video

Updated: Feb 26, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K

Entity recognition from clinical texts via recurrent neural network.

Zengjian Liu1, Ming Yang2, Xiaolong Wang1

  • 1Key Laboratory of Network Oriented Intelligent Computation, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, 518055, China.

BMC Medical Informatics and Decision Making
|July 13, 2017
PubMed
Summary

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

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

Long short-term memory (LSTM) networks show strong performance in clinical entity recognition and protected health information (PHI) identification. This deep learning approach surpasses traditional methods, offering a promising avenue for clinical text analysis.

Area of Science:

  • Natural Language Processing
  • Machine Learning
  • Clinical Informatics

Background:

  • Entity recognition is crucial for clinical text analysis, with protected health information (PHI) being a key focus.
  • Traditional methods like Support Vector Machines and Conditional Random Fields have been used, but deep learning shows promise.
  • Recurrent Neural Networks (RNNs) are increasingly applied to clinical entity recognition tasks.

Purpose of the Study:

  • To comprehensively investigate the performance of Long Short-Term Memory (LSTM) networks for clinical entity recognition.
  • To evaluate LSTM's effectiveness in identifying protected health information (PHI) within clinical texts.
  • To compare LSTM's performance against traditional machine learning methods in clinical NLP tasks.

Main Methods:

Keywords:
Clinical notesDeep learningEntity recognitionRecurrent neural networkSequence labeling

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K

Related Experiment Videos

Last Updated: Feb 26, 2026

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.9K
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

10.1K
  • Utilized LSTM, a variant of RNN, for clinical entity and PHI recognition.
  • The LSTM model comprised an input layer for word representation, an LSTM layer for contextual information, and an inference layer for tagging.
  • Experiments were conducted on corpora from the 2010, 2012, and 2014 i2b2 NLP challenges.

    • Main Results:

    • LSTM achieved high micro-average F1-scores: 85.81% for 2010 medical concept extraction, 92.29% for 2012 clinical event detection, and 94.37% for 2014 de-identification.
    • LSTM's performance was competitive with state-of-the-art systems across all evaluated tasks.
    • The results demonstrate LSTM's capability in handling complex clinical text data.

    Conclusions:

    • LSTM offers significant potential for clinical entity recognition without requiring manual feature engineering.
    • LSTM outperforms traditional machine learning methods that rely on complex feature engineering.
    • Future work includes integrating clinical knowledge bases and exploring LSTM for recognizing entities in specific formats.