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 15, 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

5.0K

Interpretable clinical prediction via attention-based neural network.

Peipei Chen1,2, Wei Dong3, Jinliang Wang4

  • 1College of Biomedical Engineering and Instrumental Science, Zhejiang University, Hangzhou, China.

BMC Medical Informatics and Decision Making
|July 11, 2020
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

CAMKV is an ISG and facilitates the degradation of rabies virus phosphoprotein via SQSTM1-mediated selective autophagy.

Autophagy·2026
Same author

Correction: Discovery of penicillic acid as a chemical probe against tau aggregation in Alzheimer's disease.

Chemical science·2026
Same author

SDGD-YOLO: a lightweight detection model for assessing the ripeness of black raspberries in complex greenhouse environments.

Frontiers in plant science·2026
Same author

The success rate and aesthetic outcomes of immediate anterior implant placement based on primary stability: A retrospective study.

Medicine·2026
Same author

Organic fractions in wastewater enabled simultaneous removal of NO<sub>3</sub><sup>-</sup> and Cr(VI) under VUV<sub>185</sub> irradiation.

Journal of environmental management·2026
Same author

GRP78 promotes rabies virus entry through interacting with viral receptors.

Journal of virology·2026
This summary is machine-generated.

This study introduces an interpretable attention neural network model for clinical predictions using electronic healthcare records (EHR). The model enhances prediction accuracy and provides patient-specific insights for better healthcare decisions.

Area of Science:

  • Artificial Intelligence
  • Clinical Informatics
  • Machine Learning

Background:

  • Machine learning models are increasingly used in healthcare, leveraging electronic healthcare records (EHR).
  • However, traditional deep learning models lack transparency, making their predictions difficult to interpret in critical medical applications.
  • Interpretability is crucial for trust and clinical adoption of AI in healthcare.

Purpose of the Study:

  • To develop an interpretable deep learning model for clinical prediction tasks.
  • To address the "black-box" nature of conventional neural networks in healthcare.
  • To enhance the transparency of AI-driven clinical predictions.

Main Methods:

  • An attention neural network model was proposed, incorporating an attention mechanism.
Keywords:
Attention mechanismClinical predictionDeep learningInterpretability

Related Experiment Videos

Last Updated: Dec 15, 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

5.0K
  • This mechanism identifies and highlights critical features influencing prediction outcomes.
  • The model was evaluated on a real-world dataset for heart failure readmission prediction.

    • Main Results:

    • The proposed model achieved 66.7% accuracy and 69.1% AUC in predicting heart failure readmissions.
    • Performance surpassed baseline models, demonstrating improved predictive power.
    • Patient-specific attention weights were generated, aiding clinical understanding and treatment planning.

    Conclusions:

    • The attention neural network model successfully improves both prediction performance and interpretability.
    • The attention mechanism provides valuable insights for clinicians, supporting individualized patient care.
    • This approach offers a more transparent and reliable AI solution for clinical decision-making.