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: Dec 20, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K

Patient Representation Transfer Learning from Clinical Notes based on Hierarchical Attention Network.

Yuqi Si1, Kirk Roberts1

  • 1School of Biomedical Informatics, The University of Texas Health Science Center at Houston Houston, TX, USA.

AMIA Joint Summits on Translational Science Proceedings. AMIA Joint Summits on Translational Science
|June 2, 2020
PubMed
Summary

A novel hierarchical recurrent neural network (RNN) effectively learns patient representations from clinical notes. This model improves mortality prediction and demonstrates strong generalizability for downstream phenotyping tasks.

Related Concept Videos

Patient-centered Care01:13

Patient-centered Care

2.8K
Patient-centered care involves delivering care beyond inpatient hospitalization. Reflective practice can enhance a patient-centered approach. Reflective practice is a process of reasoning that considers all aspects of the present situation, including practicalities, learning from personal practice, and consideration of patient needs. Patients appreciate care decisions made while considering their input. Involving the patient in their care provides the patient with a sense of contribution rather...
2.8K

You might also read

Related Articles

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

Sort by
Same author

Synthesized annotation guidelines are knowledge-lite boosters for clinical information extraction.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Education Research: Integration of Trainee and Faculty Clinics at an Academic Medical Center: Improving Quality of Care and Education.

Neurology. Education·2026
Same author

Hootation: A GUI and API library for ontology validation and verbalization.

Proceedings. IEEE International Conference on Semantic Computing·2026
Same author

Clinical document metadata extraction: A scoping review.

Journal of biomedical informatics·2026
Same author

Facilitating Clinical Information Extraction with Synthetic Data and Ontology using Large Language Models.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

An application-based ontological knowledge base of medications to support health literacy and adherence for the consumer population: an aging population use case.

Journal of biomedical semantics·2026

Area of Science:

  • Artificial Intelligence in Medicine
  • Clinical Informatics
  • Natural Language Processing

Background:

  • Longitudinal clinical notes contain valuable patient information but are challenging to analyze.
  • Extracting meaningful patient representations from sequential clinical data is crucial for predictive modeling.

Purpose of the Study:

  • To develop a hierarchical attention-based recurrent neural network (RNN) for learning patient representations from longitudinal clinical notes.
  • To evaluate the model's performance on direct clinical prediction (mortality) and transfer learning (phenotype prediction).

Main Methods:

  • A hierarchical attention-based RNN with greedy segmentation was proposed to handle varying time gaps between notes.
  • The model was trained and evaluated on clinical notes for mortality prediction.

Related Experiment Videos

Last Updated: Dec 20, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

5.1K
  • Patient representations were pre-trained and transferred to downstream tasks like obesity phenotyping.

    • Main Results:

    • The proposed hierarchical RNN model achieved superior performance in mortality prediction compared to baseline methods.
    • Attention weights provided insights into influential parts of clinical notes for mortality prediction, offering interpretability.
    • Transfer learning using pre-trained representations proved effective and generalizable for phenotype prediction tasks.

    Conclusions:

    • Hierarchical RNNs with appropriate segmentation are effective for analyzing longitudinal clinical text.
    • The developed model can generate robust patient representations for both direct prediction and transfer learning applications.
    • This approach enhances the utility of electronic health records for clinical decision support and research.