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

Evaluating Automatic Methods to Extract Patients' Supplement Use from Clinical Reports.

Yadan Fan1, Lu He2, Rui Zhang3

  • 1Institute for Health Informatics, University of Minnesota, Minneapolis, MN, USA.

Proceedings. IEEE International Conference on Bioinformatics and Biomedicine
|January 9, 2018
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

Breast Milk Stem Cells in the Treatment of Neonatal Diseases.

Current stem cell research & therapy·2025
Same author

Brain functional connectivity and activity during motor control in children with cerebral palsy: a pilot cross-sectional fNIRS study.

Translational pediatrics·2025
Same author

Clinicopathologic and molecular mutational analysis of inflammatory fibroid polyps.

Journal of the Formosan Medical Association = Taiwan yi zhi·2025
Same author

Bacillus subtilis spore surface display enhances manganese peroxidase stability and stress resistance.

Bioresources and bioprocessing·2025
Same author

Assessing the accuracy and explainability of using ChatGPT to evaluate the quality of health news.

BMC public health·2025
Same author

Using Large Language Models for sentiment analysis of health-related social media data: empirical evaluation and practical tips.

AMIA ... Annual Symposium proceedings. AMIA Symposium·2025

This study developed automated methods to track dietary supplement use from clinical notes. A rule-based classifier outperformed machine learning, accurately identifying supplement status for patient safety surveillance.

Area of Science:

  • Pharmacovigilance
  • Clinical Informatics
  • Natural Language Processing

Background:

  • Dietary supplements are widely used, raising concerns about safety and efficacy.
  • Clinical notes contain valuable data for supplement safety surveillance.
  • Accurate identification of supplement use status is crucial for safety monitoring.

Purpose of the Study:

  • To develop and compare rule-based and machine learning classifiers for automated identification of dietary supplement use status.
  • To classify supplement usage into Continuing (C), Discontinued (D), Started (S), and Unclassified (U) categories.
  • To evaluate the performance of the developed classifiers using clinical notes.

Main Methods:

  • Development of rule-based and machine learning-based classification models.
Keywords:
Clinical NotesElectronic Health recordsMachine LearningNatural Language Processing

Related Experiment Videos

  • Training and evaluation of classifiers on datasets extracted from clinical notes.
  • Analysis of classification performance using F-measure for each use status.

    • Main Results:

    • The rule-based classifier demonstrated superior performance compared to the machine learning classifier.
    • Achieved F-measure scores for the rule-based classifier were 0.93 (C), 0.98 (D), 0.95 (S), and 0.83 (U).
    • Error analysis of the rule-based classifier was conducted for further refinement.

    Conclusions:

    • Automated classification of supplement use status from clinical notes is feasible and effective.
    • Rule-based systems show promise for supplement safety surveillance in clinical practice.
    • This approach can support research and enhance patient safety related to dietary supplement consumption.