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 Video

Updated: Apr 2, 2026

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

2.4K

Denoising autoencoder framework for reconstructing missing periodontal clinical records.

Asok Mathew1, Pradeep Kumar Yadalam2

  • 1Department of Clinical Sciences, College of Dentistry, Centre for Medical and Bioallied Health Sciences Research, Ajman University, Ajman, United Arab Emirates.

Frontiers in Dental Medicine
|April 1, 2026
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

Automated detection of basement-membrane breaches in oral squamous cell carcinoma : A comparative study of convolutional neural network architectures.

Journal of oral biology and craniofacial research·2026
Same author

Keras Slim ResNet-Based Prediction of Furcation Management Recommendations Among Dentists.

International journal of dentistry·2026
Same author

Comparative Performance Evaluation of GCN, GAT, and GraphSAGE Architectures for Drug-Gene Interaction Prediction in Ameloblastoma via MEK-Pathway Targeting.

Asian Pacific journal of cancer prevention : APJCP·2026
Same author

Comparing gradient boosting and neural networks in the prediction of intersecting genes in gingival epithelial immunity.

Journal of Indian Society of Periodontology·2026
Same author

Causal digital twin modeling of periodontal healing: personalized prediction of low-level laser therapy benefit using a tooth-graph ODE transformer.

Frontiers in dental medicine·2026
Same author

Is MRI still the gold standard for assessing disc position in Temporomandibular joint disorders? A clinical-Imaging agreement study.

Cranio : the journal of craniomandibular practice·2026
Same journal

Salivary biomarker profiling in prediabetes-associated periodontitis: role of adiponectin, resistin, and total matrix metalloproteinase-8.

Frontiers in dental medicine·2026
Same journal

Harnessing generative artificial intelligence for periodontitis prediction: a machine learning approach integrating systemic health indicators for precision oral health in resource-limited settings.

Frontiers in dental medicine·2026
Same journal

Morphological evaluation of incisive canal between dentate and maxillary central incisor loss subjects in a Vietnamese population using cone beam computed tomography: a retrospective cross-sectional study.

Frontiers in dental medicine·2026
Same journal

Dental management considerations in a child with sequelae of infantile cortical hyperostosis (Caffey disease): a case report.

Frontiers in dental medicine·2026
Same journal

Three-dimensional condylar and glenoid fossa changes following functional appliance therapy in class II malocclusion: a systematic review.

Frontiers in dental medicine·2026
Same journal

Unusual denture-associated oral squamous papilloma with koilocytosis: a case report and literature review.

Frontiers in dental medicine·2026
See all related articles

Generative models effectively reconstruct missing periodontal data, improving dataset completeness for research. This approach offers a practical framework for handling missing clinical information in periodontology.

Area of Science:

  • Periodontal research
  • Data science
  • Machine learning

Background:

  • Missing clinical data present a significant challenge in periodontal research, hindering retrospective analyses and predictive modeling.
  • Traditional imputation methods often fail to capture complex variable correlations and can generate unrealistic data values.

Purpose of the Study:

  • To examine the application of generative models for reconstructing missing periodontal clinical records.
  • To outline a comprehensive workflow for data generation, imputation, and evaluation using generative models.

Main Methods:

  • A synthetic periodontal dataset of 200 virtual patients was created, including demographic and tooth-level measurements.
  • 15% of clinical variables were randomly masked to simulate missing data.
Keywords:
artificial intelligenceclinical datamissing valuesperiodontitissynthetic data

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K

Related Experiment Videos

Last Updated: Apr 2, 2026

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures
09:10

Digital Hybrid Model Preparation for Virtual Planning of Reconstructive Dentoalveolar Surgical Procedures

Published on: August 5, 2021

2.4K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

2.0K
  • A denoising autoencoder was trained to reconstruct the original data from corrupted inputs for imputation.

    • Main Results:

    • The generative model achieved a Mean Absolute Error (MAE) of 0.61 and Root Mean Squared Error (RMSE) of 0.74.
    • Imputed values closely matched the original data distributions.
    • Attachment loss and bleeding on probing showed lower imputation errors compared to probing depth and furcation involvement.

    Conclusions:

    • Generative models offer a practical framework for improving data completeness in periodontal research without introducing unrealistic values.
    • The study provides a template workflow for researchers addressing missing clinical data.
    • Future research should explore advanced models and multimodal data integration.