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: Jul 14, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

Large-scale optimization-based classification models in medicine and biology.

Eva K Lee1

  • 1Center for Operations Research in Medicine and HealthCare, School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA 30332-0205, USA. eva.lee@isye.gatech.edu

Annals of Biomedical Engineering
|May 16, 2007
PubMed
Summary

This study introduces versatile classification models for biological and medical data, achieving 80-100% accuracy in diverse applications from disease diagnosis to genomic 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

Data-Driven Evidence-Based Patient-Centered Optimal Initiation Time for Dialysis Treatment.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

Data-Driven Approach to Design an Efficient Mass Vaccination and Public Health Monitoring Informatics Platform.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2026
Same author

Temporal and spatial analysis of over 7,000 measles cases outbreak from 2018 to 2019 in the Brazilian Amazon.

Einstein (Sao Paulo, Brazil)·2024
Same author

New PK/PD model directly links diabetes drug dose to blood glucose level for personalized care.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2023
Same author

Analyzing Strategies for Containing Avian Influenza.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2023
Same author

Strategies for Disease Containment: A Biological-Behavioral-Intervention Computational Informatics Framework.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2022

Area of Science:

  • Computational Biology
  • Medical Informatics
  • Machine Learning

Background:

  • Large, heterogeneous biological and medical datasets present significant classification challenges.
  • Existing models often struggle with multi-group classification, diverse data types, and noise.
  • Over-training and high misclassification rates are common issues in predictive modeling.

Purpose of the Study:

  • To develop general-purpose, optimization-based classification models for biological and medical data.
  • To create a flexible predictive engine capable of handling complex, heterogeneous datasets.
  • To improve the accuracy and reliability of predictive rules in medical and biological applications.

Main Methods:

  • Incorporation of multi-group classification and heterogeneous attribute inputs.

Related Experiment Videos

Last Updated: Jul 14, 2026

Constructing and Visualizing Models using Mime-based Machine-learning Framework
06:19

Constructing and Visualizing Models using Mime-based Machine-learning Framework

Published on: July 22, 2025

  • High-dimensional data transformation for noise and error reduction.
  • Implementation of misclassification constraints, reserved-judgment regions, and multi-stage classification.

    • Main Results:

    • The models demonstrated correct classification rates ranging from 80% to 100% across various applications.
    • Successful application to diverse problems including disease diagnosis, genomic analysis, and medical imaging.
    • Effective handling of complex data with noise and errors through advanced transformation techniques.

    Conclusions:

    • The novel classification models offer a powerful and flexible tool for biological and medical data analysis.
    • The models' high accuracy and robustness support their use in medical diagnostics and decision-making.
    • The approach addresses key limitations of existing predictive models for complex biological systems.