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

Classifying vertical facial deformity using supervised and unsupervised learning.

P Hammond1, T J Hutton, Z L Nelson-Moon

  • 1Eastman Dental Institute for Oral Health Care Sciences, University College London, UK. p.hammond@eastman.ucl.ac.uk

Methods of Information in Medicine
|January 5, 2002
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

Time in range: A best practice guide for UK diabetes healthcare professionals in the context of the COVID-19 global pandemic.

Diabetic medicine : a journal of the British Diabetic Association·2020
Same author

The DIY artificial pancreas system: an ethical dilemma for doctors.

Diabetic medicine : a journal of the British Diabetic Association·2020
Same author

The effect of a multi-target protocol on cetacean detection and abundance estimation in aerial surveys.

Royal Society open science·2019
Same author

Working with Insulin, Carbohydrates, Ketones and Exercise to Manage Diabetes (WICKED): evaluation of a self-management course for young people with Type 1 diabetes.

Diabetic medicine : a journal of the British Diabetic Association·2019
Same author

Expanding the Menu of HIV Prevention Options: A Qualitative Study of Experiences with Long-Acting Injectable Cabotegravir as PrEP in the Context of a Phase II Trial in the United States.

AIDS and behavior·2018
Same author

The enduring impact of neurulation stage alcohol exposure: A combined behavioral and structural neuroimaging study in adult male and female C57BL/6J mice.

Behavioural brain research·2017
Same journal

Design and methodological development of a digital clinical safety training programme informed by a national framework: a New Zealand case study.

Methods of information in medicine·2026
Same journal

Panic Prediction from Digital Phenotyping: Subject-Level Cross-Validation Reveals Limited Between-Person Generalization.

Methods of information in medicine·2026
Same journal

Agent-Based Modeling Approach for Population Dynamics of the Biological Vector Aedes Aegypti.

Methods of information in medicine·2026
Same journal

A Statistical Framework for Person-centered Analysis of Digital Service Use in Public Health and Social Care.

Methods of information in medicine·2026
Same journal

Assessing the Quality of Electronic Discharge Summaries: A Cross-Sectional Study Using the Validated Spanish Version of the PDQI-9.

Methods of information in medicine·2026
Same journal

A Knowledge Graph-Driven Hypergeometric Efficacy Prediction Model for Classical Traditional Chinese Herbal Formulas.

Methods of information in medicine·2026
See all related articles

Machine learning can classify vertical facial height, but current methods have limitations. Unsupervised techniques like the Point Distribution Model (PDM) show promise for objective classification, though further research is needed for clinical use.

Area of Science:

  • Orthodontics and Dentofacial Orthopedics
  • Artificial Intelligence in Medicine
  • Medical Imaging Analysis

Background:

  • Vertical facial deformity classification relies on subjective clinical assessment.
  • Objective criteria are needed to improve diagnostic accuracy and treatment planning.
  • Machine learning (ML) offers potential for developing objective classification methods.

Purpose of the Study:

  • To explore the utility of ML techniques for objectively classifying vertical facial deformity.
  • To compare different ML approaches, including supervised and unsupervised methods.
  • To assess the clinical applicability and potential biases of these ML models.

Main Methods:

  • Analysis of 19 parameters from 131 lateral skull radiographs.

Related Experiment Videos

  • Application of supervised learning (C5.0 decision trees) and unsupervised learning (Kohonen feature maps, Point Distribution Model - PDM).
  • Evaluation of classification results against clinician assessments and parameter weighting.

    • Main Results:

    • Supervised learning (C5.0) identified clinician-specific classification rules but exhibited bias, limiting objective research use.
    • Unsupervised algorithms, particularly PDM, provided visual insights into facial growth patterns and showed potential for objectivity.
    • Discrepancies were observed between clinician reliance on specific facial parameters, highlighting individual diagnostic approaches.

    Conclusions:

    • Current ML and statistical methods for vertical facial height classification have limited clinical applicability due to process invisibility.
    • Unsupervised ML, especially PDM, shows promise for objective classification and analysis of complex cases.
    • Further research with larger datasets and diverse clinician input is necessary to refine ML tools for clinical use in facial deformity assessment.