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

Variable optimisation of medical image data by the learning Bayesian Network reasoning.

A Orun1, N Aydin

  • 1Orun Computer Consultancy in Birmingham - UK. orun@orun-scientific.co.uk

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
|November 25, 2010
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

Resistance of Single-shade Composites to Discoloration.

Operative dentistry·2022
Same author

Female university students' knowledge and practice of breast self-examination in Turkey.

Nigerian journal of clinical practice·2019
Same author

Cutaneous drug reactions to antiepileptic drugs and relation with HLA alleles in the Turkish population.

European annals of allergy and clinical immunology·2018
Same author

eNOS and XRCC4 VNTR variants contribute to formation of nicotine dependence and/or schizophrenia.

Bratislavske lekarske listy·2017
Same author

Approach to the Porta Hepatis During Cytoreductive Surgery: Technical Considerations.

Annals of surgical oncology·2015
Same author

Extensive surgical history prior to cytoreductive surgery and hyperthermic intraperitoneal chemotherapy is associated with poor survival outcomes in patients with peritoneal mucinous carcinomatosis of appendiceal origin.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2015

This study introduces a Bayesian non-linear classifier to improve medical diagnosis by selecting key data attributes. This method reduces uncertainty and prevents overfitting, enhancing classification accuracy and potentially lowering clinical data costs.

Area of Science:

  • Artificial Intelligence
  • Machine Learning
  • Medical Informatics

Background:

  • Medical diagnosis relies on accurate classification of complex patient data.
  • High dimensionality and redundancy in clinical data can lead to uncertainty and overfitting.
  • Existing classification methods may struggle with large datasets, impacting accuracy and cost.

Purpose of the Study:

  • To develop a novel Bayesian non-linear classifier for optimal attribute subset selection in medical diagnosis.
  • To leverage Bayesian Networks (BN) for structural reasoning to prevent overfitting and maintain high classification accuracy.
  • To simplify complex data analysis and reduce costs associated with clinical data acquisition.

Main Methods:

  • Utilized a Bayesian non-linear classifier for attribute selection.

Related Experiment Videos

  • Employed Bayesian Networks (BN) for structural reasoning and attribute optimization.
  • Focused on reducing data uncertainty and preventing overfitting in the classification process.

    • Main Results:

    • Successfully identified an optimal subset of attributes, minimizing redundancy.
    • Achieved high classification accuracy while preventing model overfitting.
    • Demonstrated a simplified approach to complex medical data analysis.

    Conclusions:

    • The proposed Bayesian non-linear classifier effectively enhances medical diagnosis.
    • This method offers a robust solution for managing high-dimensional clinical data.
    • Potential for significant cost reduction in clinical data acquisition and analysis.