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

Data mining in medical time series.

Ralf Mikut1, Markus Reischl, Ole Burmeister

  • 1Forschungszentrum Karlsruhe GmbH, Institute for Applied Computer Science, Karlsruhe, Germany. ralf.mikut@iai.fzk.de

Biomedizinische Technik. Biomedical Engineering
|December 13, 2006
PubMed
Summary

This study introduces a computer-based method for analyzing medical data using data mining. It enables better comparison of medical conditions through feature extraction and tailored evaluations.

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

Ultra-High-Throughput Discovery of Multifunctional Polyphenolic Coatings on Droplet Microarrays.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Explainable time-series forecasting with sampling-free SHAP for Transformers.

Nature communications·2026
Same author

A kinetics-based model of haematopoiesis reveals extrinsic regulation of skewed lineage output from stem cells.

Nature cell biology·2026
Same author

Helical opto-thermoviscous flows drive out-of-plane rotation and particle spinning in a highly viscous micro-environment.

Light, science & applications·2026
Same author

Large-area 3D reconstruction of corneal tissues from oscillating focus confocal microscopy.

Scientific reports·2026
Same author

A method for the evaluation of automated solid dosing technologies for mid-scale dosing tasks in laboratory automation.

SLAS technology·2026

Area of Science:

  • Computer Science
  • Biomedical Engineering
  • Data Mining

Background:

  • Medical problem description and comparison often lack standardized, quantitative methods.
  • Existing approaches may not adequately handle complex time-series data or specific evaluation criteria.

Purpose of the Study:

  • To propose a modular, computer-based methodology for describing and comparing medical problems.
  • To apply data mining techniques for systematic feature extraction and classification.
  • To develop an evaluation framework adaptable to specific constraints.

Main Methods:

  • Mathematical formulation of classification problems.
  • Systematic extraction of interpretable features from time-series data.
  • Development of an evaluation metric considering computational power and interpretability.

Related Experiment Videos

Main Results:

  • The methodology was successfully applied to instrumented gait analysis.
  • It was also effective in the individual design of myoelectric controllers for prostheses.
  • Demonstrated the utility of data mining for complex biomedical applications.

Conclusions:

  • The proposed methodology offers a robust framework for medical problem analysis.
  • It facilitates quantitative comparison and personalized design in biomedical engineering.
  • Highlights the potential of data mining in advancing clinical and prosthetic applications.