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

Searching for risk factors using multilayer neural network as a classifier

H Xue1, N Tatsumi, K Park

  • 1Department of Statistics, Chinese Academy of Preventive Medicine, Beijing, China.

Medical Informatics = Medecine Et Informatique
|July 1, 1996
PubMed
Summary

This study introduces a novel method using neural networks to identify risk factors for specific outcomes. By analyzing output differentials, it pinpoints key input variables influencing results.

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

[Examining the origin of the Zheng's in Kunshan and their medical physicians].

Zhonghua yi shi za zhi (Beijing, China : 1980)·2026
Same author

Species diversity of <i>Cytospora</i> associated with forest canker diseases in Xizang (Tibet), China.

Persoonia·2026
Same author

Cardiovascular magnetic resonance to differentiate veteran athlete's heart with cavity dilatation and mild dilated cardiomyopathy.

European heart journal. Cardiovascular Imaging·2025
Same author

[Predictive value of liver-to-spleen volume ratio for short-term prognosis in patients with hepatitis B virus-related acute-on-chronic liver failure].

Zhonghua yi xue za zhi·2025
Same author

Detection of water adulteration levels in milk using near-infrared spectroscopy combined with chemometrics.

Journal of dairy science·2025
Same author

[The versions of <i>Song Xin Notes</i> and their content].

Zhonghua yi shi za zhi (Beijing, China : 1980)·2025

Area of Science:

  • Machine Learning
  • Biostatistics
  • Computational Biology

Background:

  • Identifying risk factors is crucial for predicting health outcomes.
  • Traditional methods may not capture complex, non-linear relationships.
  • Neural networks offer powerful tools for analyzing intricate data patterns.

Purpose of the Study:

  • To propose a novel method for determining risk factors for specific outcomes.
  • To leverage multilayer neural networks for risk factor identification.
  • To establish a quantitative approach for assessing variable influence.

Main Methods:

  • Utilizing trained multilayer neural networks.
  • Calculating partial differentials of the network's output with respect to input variables.

Related Experiment Videos

  • Assuming differentiable activation functions and continuity of input variables.

    • Main Results:

    • The proposed method quantifies the influence of input variables on network output.
    • Partial differentials serve as a measure to determine risk factor significance.
    • This approach enables a data-driven identification of key predictive factors.

    Conclusions:

    • The method provides a robust framework for risk factor determination using neural networks.
    • It offers a valuable tool for fields requiring outcome prediction and risk assessment.
    • Further research can explore applications in diverse scientific domains.