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 Video

Updated: May 13, 2026

An Orthotopic Bladder Tumor Model and the Evaluation of Intravesical saRNA Treatment
08:43

An Orthotopic Bladder Tumor Model and the Evaluation of Intravesical saRNA Treatment

Published on: July 28, 2012

Urinary nucleosides as potential tumor markers evaluated by learning vector quantization.

Frank Dieterle1, Silvia Müller-Hagedorn, Hartmut M Liebich

  • 1Institute of Physical and Theoretical Chemistry, Auf der Morgenstelle 8, D-72076 Tübingen, Germany. frank.dieterle@ipc.uni-tuebingen.de

Artificial Intelligence in Medicine
|August 21, 2003
PubMed
Summary

Learning vector quantization (LVQ) shows promise for breast cancer detection using urinary nucleoside levels. This method offers reproducible and efficient pattern recognition compared to backpropagation (BP) and support vector machines (SVM) for tumor marker analysis.

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

Morphometric Findings in Adolescents with Robin Sequence: A Photographic and Cephalometric Study of the Face and Mandible.

Children (Basel, Switzerland)·2026
Same author

Spotlight on sensors as tools for biointelligence.

Analytical and bioanalytical chemistry·2026
Same author

Orthodontic Perspectives in the Interdisciplinary Management of Pediatric Obstructive Sleep Apnea.

Children (Basel, Switzerland)·2025
Same author

Accurate calculation of affinity changes to the close state of influenza A M2 transmembrane domain in response to subtle structural changes of adamantyl amines using free energy perturbation methods in different lipid bilayers.

Biochimica et biophysica acta. Biomembranes·2023
Same author

(R)evolution of the Standard Addition Procedure for Immunoassays.

Biosensors·2023
Same author

Tools to compare antibody gold nanoparticle conjugates for a small molecule immunoassay.

Mikrochimica acta·2023

Area of Science:

  • Biochemistry
  • Computational Biology
  • Oncology

Background:

  • Modified nucleosides in urine show distinct patterns between breast cancer patients and healthy individuals.
  • Accurate pattern recognition is crucial for utilizing urinary nucleoside levels as breast cancer tumor markers.
  • Existing methods like backpropagation (BP) neural networks are common, but superior alternatives like learning vector quantization (LVQ) and support vector machines (SVM) exist.

Purpose of the Study:

  • To evaluate the performance of LVQ for classifying urinary nucleoside levels in breast cancer detection.
  • To compare the efficacy of LVQ against BP and SVM neural networks in this diagnostic application.
  • To assess the feasibility of using urinary nucleoside profiles for breast cancer screening.

Main Methods:

More Related Videos

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System
06:23

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

Published on: January 12, 2017

CRISPR-Cas-mediated Multianalyte Synthetic Urine Biomarker Test for Portable Diagnostics
04:33

CRISPR-Cas-mediated Multianalyte Synthetic Urine Biomarker Test for Portable Diagnostics

Published on: December 8, 2023

Related Experiment Videos

Last Updated: May 13, 2026

An Orthotopic Bladder Tumor Model and the Evaluation of Intravesical saRNA Treatment
08:43

An Orthotopic Bladder Tumor Model and the Evaluation of Intravesical saRNA Treatment

Published on: July 28, 2012

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System
06:23

A Murine Orthotopic Bladder Tumor Model and Tumor Detection System

Published on: January 12, 2017

CRISPR-Cas-mediated Multianalyte Synthetic Urine Biomarker Test for Portable Diagnostics
04:33

CRISPR-Cas-mediated Multianalyte Synthetic Urine Biomarker Test for Portable Diagnostics

Published on: December 8, 2023

  • Urine samples were collected from female breast cancer patients and healthy controls.
  • Twelve ribonucleosides were isolated and quantified using high-performance liquid chromatography (HPLC).
  • LVQ, SVM, and BP neural networks were trained and tested for classification accuracy.

Main Results:

  • All evaluated methods (LVQ, SVM, BP) demonstrated good classification performance.
  • Sensitivity ranged from 58.8% to 70.6%, with specificity between 88.4% and 94.2%.
  • LVQ exhibited superior qualitative features, including reproducibility, efficient training with unbalanced data, and speed.

Conclusions:

  • LVQ presents advantages over BP and SVM for breast cancer detection using urinary nucleoside patterns.
  • LVQ's reproducibility, training efficiency, and adaptability make it suitable for medical decision support systems.
  • Further extended studies are recommended to validate LVQ's clinical utility in breast cancer diagnostics.