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 Videos

Risk stratification in heart failure using artificial neural networks.

F Atienza1, N Martinez-Alzamora, J A De Velasco

  • 1Cardiology Department, University General Hospital, Valencia, Spain. fatienzaf@meditex.es

Proceedings. AMIA Symposium
|November 18, 2000
PubMed
Summary

Neural networks accurately predict heart failure prognosis, classifying patients into death, readmission, or event-free survival groups. This tool shows promise for improving heart failure patient management and outcomes.

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

Phase singularity point tracking for the identification of typical and atypical flutter patients: A clinical-computational study.

Computers in biology and medicine·2018
Same author

Minimal configuration of body surface potential mapping for discrimination of left versus right dominant frequencies during atrial fibrillation.

Pacing and clinical electrophysiology : PACE·2017
Same author

Training in Health Informatics in Brazil.

Yearbook of medical informatics·2016
Same author

Arrhythmia ablation using the Amigo Robotic Remote Catheter System versus manual ablation: One year follow-up results.

International journal of cardiology·2015
Same author

Creating a Common Data Model for Comparative Effectiveness with the Observational Medical Outcomes Partnership.

Applied clinical informatics·2015
Same author

Health IT and clinical decision support systems: human factors and successful adoption.

Journal of the American Medical Informatics Association : JAMIA·2014

Area of Science:

  • Cardiology
  • Medical Informatics
  • Artificial Intelligence in Medicine

Background:

  • Accurate risk stratification is crucial for effective heart failure management and improving patient outcomes.
  • Heart failure presents as a complex multisystem disease with numerous categorical predictors.
  • Neural network models have demonstrated success in various medical classification tasks.

Purpose of the Study:

  • To assess the one-year prognosis of heart failure patients using a simple neural network model.
  • To classify patients into three distinct outcome groups: death, readmission, and one-year event-free survival.
  • To identify relevant predictors for heart failure prognosis using the Automatic Relevance Determination (ARD) method.

Main Methods:

  • A simple neural network model was employed to analyze the one-year prognosis of 132 heart failure patients.

Related Experiment Videos

  • A resampling method was utilized for training the neural network due to a small patient cohort.
  • The Automatic Relevance Determination (ARD) method was used to identify significant predictors and estimate their impact on outcomes.

    • Main Results:

    • The neural network model achieved high accuracy, misclassifying only 9 out of 132 patients.
    • Relevant predictors for the three outcome groups (death, readmission, event-free survival) were identified.
    • The model demonstrated effective classification of heart failure patient prognosis.

    Conclusions:

    • Simple neural networks show significant potential as a valuable tool for heart failure prognosis.
    • This approach can aid in refining patient management strategies and enhancing clinical outcomes.
    • Further application of neural networks in cardiology may lead to improved diagnostic and prognostic capabilities.