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

Combining logistic regression and neural networks to create predictive models.

K A Spackman1

  • 1Biomedical Information Communication Center, Oregon Health Sciences University, Portland.

Proceedings. Symposium on Computer Applications in Medical Care
|January 1, 1992
PubMed
Summary
This summary is machine-generated.

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

Normal forms for description logic expressions of clinical concepts in SNOMED RT.

Proceedings. AMIA Symposium·2002
Same author

SNOMED clinical terms: overview of the development process and project status.

Proceedings. AMIA Symposium·2002
Same author

Mapping between SNOMED RT and Clinical terms version 3: a key component of the SNOMED CT development process.

Proceedings. AMIA Symposium·2002
Same author

Terminology convergence: SNOMED gets a boost.

M.D. computing : computers in medical practice·1999
Same author

Integrating sources for a clinical reference terminology: experience linking SNOMED to LOINC and drug vocabularies.

Studies in health technology and informatics·1999
Same author

Compositional concept representation using SNOMED: towards further convergence of clinical terminologies.

Proceedings. AMIA Symposium·1999

Neural networks and logistic regression share similarities. A modified logistic regression aids in training neural networks for variable selection and predictive modeling in medicine.

Area of Science:

  • Computational biology
  • Machine learning in medicine
  • Statistical modeling

Background:

  • Neural networks are increasingly utilized for predictive modeling across various scientific domains, including medicine.
  • Logistic regression is a statistical method with strong parallels to neural network functionality.

Purpose of the Study:

  • To elucidate the similarities between neural networks and logistic regression.
  • To introduce a modified logistic regression technique for neural network training.
  • To demonstrate the application of this modification in variable selection and predictive model building.

Main Methods:

  • Comparative analysis of neural networks and logistic regression.
  • Development of a modified logistic regression algorithm.

Related Experiment Videos

  • Application of the modified algorithm for variable selection and predictive modeling using neural networks.

    • Main Results:

    • Established key similarities between neural networks and logistic regression.
    • Demonstrated the efficacy of the modified logistic regression in neural network training.
    • Successfully applied the method for variable selection and predictive model building.

    Conclusions:

    • The modified logistic regression offers a valuable approach for enhancing neural network training.
    • This method facilitates improved variable selection and predictive model performance.
    • The findings have implications for the application of neural networks in data-driven fields like medicine.