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

An Epicurean learning approach to gene-expression data classification.

Andreas Albrecht1, Staal A Vinterbo, Lucila Ohno-Machado

  • 1Computer Science Department, University of Hertfordshire, Hatfield, Herts AL10 9AB, UK. a.albrecht@herts.ac.uk

Artificial Intelligence in Medicine
|July 10, 2003
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

Development of the authentication and authorization processes for the iAgree portal, a platform for patient-controlled data sharing across health systems.

JAMIA open·2026
Same author

Foundation Model-Guided Synthetic EHR Release: Performance Enhancement with Privacy Preservation.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Large Models for Small Tables: Adapting Tabular Foundation Models to EHR Data.

AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science·2026
Same author

Memorization in large language models in medicine prevalence characteristics and implications.

Nature communications·2026
Same author

Privacy-enhancing sequential learning under heterogeneous selection bias in multi-site electronic health records data.

Journal of the American Medical Informatics Association : JAMIA·2026
Same author

Exploring patient motivations and preferences for medical data sharing with researchers: a simulation study using the iAgree platform.

Journal of the American Medical Informatics Association : JAMIA·2026
Same journal

Real-time EEG-based epileptic seizure prediction using artificial intelligence: A systematic review.

Artificial intelligence in medicine·2026
Same journal

R-peak detection and ECG data compression scheme based on empirical mode decomposition and wavelet transform.

Artificial intelligence in medicine·2026
Same journal

CastNet: A three-channel EEG-based deep learning model for cross-subject depression detection.

Artificial intelligence in medicine·2026
Same journal

State-of-the-art TinyML approaches for colorectal cancer detection: Current advances, challenges, and future directions.

Artificial intelligence in medicine·2026
Same journal

JRadiEvo: A Japanese radiology report generation model enhanced by evolutionary optimization of model merging.

Artificial intelligence in medicine·2026
Same journal

Causally-informed deep learning towards explainable and generalizable outcome prediction in critical care.

Artificial intelligence in medicine·2026
See all related articles

Perceptrons effectively classify tumor types using gene expression data. Feature selection is crucial for accurate diagnosis of small round blue cell tumors and leukemia.

Area of Science:

  • Bioinformatics
  • Computational Biology
  • Machine Learning

Background:

  • Accurate classification of childhood cancers like small round blue cell tumors (SRBCT) is challenging.
  • Distinguishing between acute myeloid leukemia (AML) and acute lymphoblastic leukemia (ALL) requires sophisticated methods.

Purpose of the Study:

  • To evaluate the efficacy of perceptrons for classifying microarray gene-expression data.
  • To develop and validate a feature selection method for identifying significant genes in tumor classification.

Main Methods:

  • Utilized perceptrons trained with a simulated annealing-based method and resampling.
  • Applied the method to two well-known datasets: SRBCT and the AML/ALL classification problem.
  • Implemented a novel feature selection approach to identify key genes for tumor classification.

Related Experiment Videos

Main Results:

  • Perceptron classification performance was comparable to existing methods for SRBCT and AML/ALL.
  • Achieved high accuracy with minimal gene sets: 13 genes for SRBCT and 9 genes for AML/ALL.
  • Demonstrated the critical role of feature selection and simulated annealing in achieving optimal classification results.

Conclusions:

  • Perceptrons are a viable tool for tumor classification using gene-expression data.
  • Feature selection is essential for building accurate and parsimonious models.
  • Combined approaches of Epicurean-style learning and simulated annealing enhance classification performance.