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 techniques applied to medical information.

I N Lee1, S C Liao, M Embrechts

  • 1Lally School of Management and Technology, Rensselaer Polytechnic Institute (RPI), Troy, NY, USA. leei@rpi.edu

Medical Informatics and the Internet in Medicine
|July 20, 2000
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

Patients with chronic urticaria have a higher risk of psychiatric disorders: a population-based study.

The British journal of dermatology·2019
Same author

Conduction control at ferroic domain walls via external stimuli.

Nanoscale·2014
Same author

Antidepressant-associated mania: soon after switch from fluoxetine to mirtazapine in an elderly woman with mixed depressive features.

Journal of psychopharmacology (Oxford, England)·2008
Same author

Successful treatment of persistent bacteremia after endoscopic injection of N-butyl-2-cyanoacrylate for gastric varices bleeding.

Endoscopy·2007
Same author

A missing data treatment for data mining applications in medical information systems.

The Kaohsiung journal of medical sciences·2001
Same author

Deletion mapping of chromosome 16q24 in hepatocellular carcinoma in Taiwan and mutational analysis of the 17-beta-HSD gene localized to the region.

International journal of cancer·2001
Same journal

Patients' perceptions of Internet usage and their opportunity to obtain health information.

Medical informatics and the Internet in medicine·2007
Same journal

Assisting the transition from hospital to home for children with major congenital heart disease by telemedicine: a feasibility study and initial results.

Medical informatics and the Internet in medicine·2007
Same journal

Digital pens and pain diaries in palliative home health care: professional caregivers' experiences.

Medical informatics and the Internet in medicine·2007
Same journal

Readability and cultural sensitivity of web-based patient decision aids for cancer screening and treatment: a systematic review.

Medical informatics and the Internet in medicine·2007
Same journal

ICT-based health information services for elderly people: past experiences, current trends, and future strategies.

Medical informatics and the Internet in medicine·2007
Same journal

Obtrusiveness of information-based assistive technologies as perceived by older adults in residential care facilities: a secondary analysis.

Medical informatics and the Internet in medicine·2007
See all related articles

Data mining techniques effectively extract knowledge from medical data to identify high-risk heart disease patients and key contributing factors. Neural networks offer superior classification accuracy compared to discriminant analysis.

Area of Science:

  • Medical Informatics
  • Data Science
  • Cardiology

Background:

  • Medical information systems generate vast amounts of data, presenting challenges for knowledge discovery.
  • Current methods for extracting actionable insights from this data are often complex and not widely accessible.

Purpose of the Study:

  • To apply accessible data mining techniques for enhanced functionality of medical information systems.
  • To identify high-risk patients and critical factors in heart disease using data mining.

Main Methods:

  • Application of data mining techniques: data visualization, correlation analysis, discriminant analysis, and neural network supervised classification.
  • Utilized nonparametric classification tools for identifying high-risk heart disease patients.
  • Explored methods for handling missing data within the analysis.

Related Experiment Videos

Main Results:

  • Neural networks achieved higher correct classification rates (89%) for heart disease patients than discriminant analysis (79%).
  • Data visualization and correlation analysis identified similar key factors contributing to heart disease.
  • A multivariate relationship model was constructed using visualization techniques.

Conclusions:

  • Data mining offers simple, effective methods for knowledge extraction from general medical information.
  • These techniques can significantly improve the identification of at-risk individuals and understanding of disease factors.
  • The study demonstrates the practical utility of data mining in clinical settings.