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 reduction using a discrete wavelet transform in discriminant analysis of very high dimensionality data.

Yinsheng Qu1, Bao-Ling Adam, Mark Thornquist

  • 1Cancer Prevention Research Program, Fred Hutchinson Cancer Research Center, 1100 Fairview Ave. N. MP-702 Seattle, Washington, USA. yqu@fhcrc.org

Biometrics
|May 24, 2003
PubMed
Summary

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

Remodeling the trauma bay to improve communication and patient care: a novel approach to trauma resuscitations.

Trauma surgery & acute care open·2025
Same author

A perspective on green, blue, and grey spaces, biodiversity, microbiota, and human health.

The Science of the total environment·2023
Same author

A Genetic Locus within the FMN1/GREM1 Gene Region Interacts with Body Mass Index in Colorectal Cancer Risk.

Cancer research·2023
Same author

Genotoxic colibactin mutational signature in colorectal cancer is associated with clinicopathological features, specific genomic alterations and better survival.

medRxiv : the preprint server for health sciences·2023
Same author

Combining Asian-European Genome-Wide Association Studies of Colorectal Cancer Improves Risk Prediction Across Race and Ethnicity.

medRxiv : the preprint server for health sciences·2023
Same author

Assessment of unmet secondary elective healthcare need-itself in need of acute care in Aotearoa New Zealand.

The New Zealand medical journal·2023

This study introduces wavelet transform for data reduction in discriminant analysis. The method effectively identified prostate cancer biomarkers, achieving high accuracy in a clinical study.

Area of Science:

  • Biostatistics
  • Biomarker Discovery
  • Genomics

Background:

  • High-dimensional data in proteomics presents challenges for discriminant analysis.
  • Traditional methods struggle when variables far exceed observations, as seen in biomarker studies.

Purpose of the Study:

  • To develop a data reduction method using wavelet transform for high-dimensional biological data.
  • To apply this method to identify significant biomarkers for prostate cancer detection.

Main Methods:

  • Utilized discrete wavelet transform to reduce dimensionality from 48,538 variables to 1271 wavelet coefficients.
  • Employed information criteria to select the most discriminatory 11 wavelet coefficients.
  • Developed a linear classifier based on selected coefficients.

Related Experiment Videos

Main Results:

  • The wavelet transform significantly reduced data complexity while preserving discriminatory information.
  • Identified 11 key wavelet coefficients with high potential for cancer detection.
  • The classifier achieved 97% sensitivity and 100% specificity for prostate cancer detection in a test set.

Conclusions:

  • Wavelet transform is an effective tool for data reduction in high-dimensional discriminant analysis.
  • This approach can successfully identify biomarkers for diseases like prostate cancer.
  • The method offers a robust strategy for analyzing complex biological datasets.