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

Maximum entropy modeling for mining patient medication status from free text.

Serguei V Pakhomov1, Alexander Ruggieri, Christopher G Chute

  • 1Division of Medical informatics Research, Department of Health Sciences Research, Mayo Clinic, Rochester, MN, USA.

Proceedings. AMIA Symposium
|December 5, 2002
PubMed
Summary

This study developed a machine learning model to automatically classify patient medication status from clinical notes. The optimized model accurately identifies medication initiation, continuation, or discontinuation with 89% predictive power.

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

Multi-scale data improves performance of machine learning model for long COVID identification.

Communications medicine·2026
Same author

Governing real-world health data as a public utility.

Science (New York, N.Y.)·2026
Same author

LinkML: an open data modeling framework.

GigaScience·2025
Same author

Development of a robust corpus for automated evaluation of online health information in Chinese using the DISCERN scale.

Journal of the American Medical Informatics Association : JAMIA·2025
Same author

Advancing the science of genomic learning healthcare systems.

Learning health systems·2025
Same author

Mondo: integrating disease terminology across communities.

Genetics·2025

Area of Science:

  • Natural Language Processing
  • Clinical Informatics
  • Machine Learning

Background:

  • Clinical documentation contains valuable patient medication information.
  • Manual extraction of medication status is time-consuming and prone to errors.
  • Automated methods are needed to efficiently process clinical text.

Purpose of the Study:

  • To develop and evaluate a machine learning model for classifying patient medication status.
  • To categorize medications as discontinued, initiated, or continued based on clinical notes.
  • To identify optimal features for accurate medication status classification.

Main Methods:

  • Utilized a Maximum Entropy (ME) machine learning technique.
  • Employed hand-labeled training data for model generation.

Related Experiment Videos

  • Tested five distinct training feature sets for classification.

    • Main Results:

    • The most effective feature set combined contextual words, sentence subject, and semantic cues.
    • This optimal feature set achieved an average predictive power of 89%.
    • The model demonstrated high accuracy in recognizing medication status changes.

    Conclusions:

    • Machine learning, specifically Maximum Entropy, can effectively classify patient medication status from clinical text.
    • Contextual and semantic features are crucial for accurate medication status recognition.
    • This approach offers a scalable solution for medication status monitoring in clinical practice.