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

Machine learning models for lung cancer classification using array comparative genomic hybridization.

C F Aliferis1, D Hardin, P P Massion

  • 1Biomedical Informatics, Vanderbilt University, Nashville, TN, USA.

Proceedings. AMIA Symposium
|December 5, 2002
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

Sex-Specific Skeletal Muscle Gene Expression Responses to Exercise Reveal Novel Direct Mediators of Insulin Sensitivity Change.

medRxiv : the preprint server for health sciences·2024
Same author

Biomedical Informatics Training Program at Vanderbilt University.

Yearbook of medical informatics·2016
Same author

Decision Support Systems.

Yearbook of medical informatics·2016
Same author

Lung cancer risk test trial: study design, participant baseline characteristics, bronchoscopy safety, and establishment of a biospecimen repository.

BMC pulmonary medicine·2016
Same author

Plasma levels of interleukin-1 receptor antagonist (IL1Ra) predict radiographic progression of symptomatic knee osteoarthritis.

Osteoarthritis and cartilage·2015
Same author

Trends and developments in bioinformatics in 2010: prospects and perspectives.

Yearbook of medical informatics·2011
Same journal

Progressive display of very high resolution images using wavelets.

Proceedings. AMIA Symposium·2002
Same journal

The Chronus II temporal database mediator.

Proceedings. AMIA Symposium·2002
Same journal

Gene expression levels in different stages of progression in oral squamous cell carcinoma.

Proceedings. AMIA Symposium·2002
Same journal

An assessment of the visibility of MeSH-indexed medical web catalogs through search engines.

Proceedings. AMIA Symposium·2002
Same journal

Filtering for medical news items using a machine learning approach.

Proceedings. AMIA Symposium·2002
Same journal

Enriching the structure of the UMLS semantic network.

Proceedings. AMIA Symposium·2002
See all related articles

Array comparative genomic hybridization (CGH) effectively classifies non-small lung cancer subtypes using gene copy number data. Machine learning models achieved high accuracy, highlighting CGH as a valuable diagnostic tool.

Area of Science:

  • Genomics
  • Oncology
  • Bioinformatics

Background:

  • Array comparative genomic hybridization (CGH) is a novel technology for assessing gene copy number alterations.
  • Accurate classification of non-small lung cancer (NSCLC) subtypes is crucial for effective treatment.

Purpose of the Study:

  • To develop and compare machine learning models for classifying NSCLC histopathology based on array CGH data.
  • To evaluate the efficacy of gene copy number profiles in distinguishing between squamous carcinomas and adenocarcinomas.

Main Methods:

  • DNA from 37 NSCLC patients (21 squamous carcinomas, 16 adenocarcinomas) was analyzed using a 452 BAC clone array CGH.
  • Machine learning algorithms including K-Nearest Neighbors (KNN), Decision Tree Induction, Support Vector Machines (SVM), and Feed-Forward Neural Networks (FFNN) were employed.

Related Experiment Videos

  • Leave-one-out cross-validation was used to assess classification accuracy.

    • Main Results:

    • The best machine learning model achieved a leave-one-out classification accuracy of 89.2%.
    • Gene copy number data collectively served as a strong indicator for histological subtyping.
    • Decision Tree Induction models demonstrated lower performance compared to other algorithms in this study.

    Conclusions:

    • Array CGH-derived gene copy number data is a highly effective biomarker for NSCLC histological subtyping.
    • Machine learning approaches, particularly SVM and FFNN, show promise for automated classification of lung cancer subtypes.
    • Further research into multi-gene models and advanced algorithms can enhance diagnostic capabilities.