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

Dental data mining: potential pitfalls and practical issues.

S A Gansky1

  • 1Center for Health and Community, Department of Preventive and Restorative Dental Sciences, Division of Oral Epidemiology and Dental Public Health, University of California, San Francisco, CA 94143-1361, USA. sgansky@ucsf.edu

Advances in Dental Research
|May 6, 2004
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

Whose Data Are They? Data Ownership and Sovereignty in Oral Health Research.

JDR clinical and translational research·2025
Same author

Quality-Adjusted Life Year Proxies for Caries in Primary Dentition: A Discrete Choice Experiment.

JDR clinical and translational research·2023
Same author

What Can We Learn from Parents of Caries-Free and Caries-Active Hispanic Children?

JDR clinical and translational research·2020
Same author

Constructing Matched Groups in Dental Observational Health Disparity Studies for Causal Effects.

JDR clinical and translational research·2019
Same author

Geography matters: state-level variation in children's oral health care access and oral health status.

Public health·2016
Same author

Understanding treatment effect mechanisms of the CAMBRA randomized trial in reducing caries increment.

Journal of dental research·2014
Same journal

Institutional Patriarchy, Gender Barriers, and Nigeria's Oral Health Workforce.

Advances in dental research·2025
Same journal

Sex, Gender and Sexuality in Oral Health Research: Setting the Scene.

Advances in dental research·2025
Same journal

Beyond Demographics: Sex, Gender, and Sexuality in Oral Health Research.

Advances in dental research·2025
Same journal

Conceptualisations of Sex and Gender in Oral Health Research.

Advances in dental research·2025
Same journal

Analysing the Interaction of Sex and Laboratory Conditions in Animal Research.

Advances in dental research·2025
Same journal

Advancing Oral Health Workforce Equity in Gender and Sexual Orientation.

Advances in dental research·2025
See all related articles

This study compares data mining methods like Artificial Neural Networks (ANN) and Classification and Regression Trees (CART) against classic regression for predicting dental caries. CART and ANN models show potential advantages in specific scenarios.

Area of Science:

  • Data Mining
  • Biostatistics
  • Machine Learning

Background:

  • Knowledge Discovery and Data Mining (KDD) are increasingly utilized in scientific research.
  • Common KDD tools include classic regression, Artificial Neural Network (ANN), and Classification and Regression Tree (CART) models.
  • ANN and CART models may offer superior performance over classic regression for specific data characteristics.

Purpose of the Study:

  • To compare the predictive performance of logistic regression with KDD methods (CART and ANN).
  • To analyze data from the Rochester caries study using these comparative methods.
  • To highlight the strengths and limitations of different data mining techniques.

Main Methods:

  • Utilized validation procedures to assess model prediction performance.

Related Experiment Videos

  • Evaluated metrics including concordance, sensitivity, specificity, and likelihood ratio.
  • Employed visualization tools like lift charts and receiver operating characteristic (ROC) curves for interpretation.

    • Main Results:

    • CART models demonstrated strength in handling covariate interactions.
    • ANN models showed proficiency with nonlinear covariates.
    • The study provided a comparative analysis of logistic regression, CART, and ANN on a dental caries dataset.

    Conclusions:

    • Careful validation and selection of appropriate comparative models are crucial to avoid pitfalls in naive data mining analyses.
    • ANN and CART models offer valuable alternatives to classic regression, particularly for complex datasets.
    • The findings underscore the importance of choosing the right data mining tools for specific research questions.