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

Data mining techniques for cancer detection using serum proteomic profiling.

Lihua Li1, Hong Tang, Zuobao Wu

  • 1Department of Radiology, College of Medicine, H. Lee Moffitt Cancer Center and Research Institute, University of South Florida, Tampa, FL 33612-4799, USA. lilh@moffitt.usf.edu

Artificial Intelligence in Medicine
|September 15, 2004
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

Right Ventricular Dissipative Energy Loss Detected by Vector Flow Mapping in Children: Characteristics of Normal Values.

Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine·2018
Same author

Photodynamic Inactivation of Multidrug-Resistant <i>Staphylococcus aureus</i> Using Hybrid Photosensitizers Based on Amphiphilic Block Copolymer-Functionalized Gold Nanoparticles.

ACS omega·2018
Same author

Bub1 Facilitates Virus Entry through Endocytosis in a Model of Drosophila Pathogenesis.

Journal of virology·2018
Same author

Antifungal photodynamic inactivation against dermatophyte Trichophyton rubrum using nanoparticle-based hybrid photosensitizers.

Photodiagnosis and photodynamic therapy·2018
Same author

Rural Households' Livelihood Capital, Risk Perception, and Willingness to Purchase Earthquake Disaster Insurance: Evidence from Southwestern China.

International journal of environmental research and public health·2018
Same author

Spatiotemporal distribution and national measurement of the global carbonate carbon sink.

The Science of the total environment·2018

Data mining techniques show promise for ovarian cancer detection using serum proteomic patterns. Genetic algorithm-based feature selection demonstrated superior accuracy and robustness compared to statistical testing for identifying cancer biomarkers.

Area of Science:

  • Biochemistry
  • Computational Biology
  • Oncology

Background:

  • Serum proteomic patterns can reflect pathological changes in tissues.
  • Unique proteomic profiles may differentiate cancer from non-cancer samples.
  • Data mining is essential for analyzing complex proteomic data to find subtle differences.

Purpose of the Study:

  • Review data mining applications in proteomics for cancer detection.
  • Explore a novel analytical method with various feature selection techniques.
  • Compare detection performance and proteomic patterns across datasets and with prior research.

Main Methods:

  • Utilized three serum Surface-Enhanced Laser Desorption/Ionization Mass Spectrometry (SELDI-MS) datasets.
  • Employed a support vector machine (SVM) classifier.

Related Experiment Videos

  • Implemented genetic algorithm (GA) and statistical testing for feature selection.
  • Evaluated performance using leave-one-out cross-validation and Receiver Operating Characteristic (ROC) curves.

    • Main Results:

    • Data mining successfully applied to ovarian cancer detection with high performance.
    • GA-based feature selection yielded better accuracy and robustness than statistical testing.
    • Discriminatory proteomic patterns varied significantly based on the selection method.

    Conclusions:

    • Data mining is effective for ovarian cancer detection using serum proteomic data.
    • Genetic algorithms offer improved feature selection for cancer biomarker identification.
    • The choice of feature selection and classifier impacts the reliability of identified cancer-related proteins.