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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

MAPK/c-Jun/TNNT1 pathway regulates cytoskeletal remodeling and promotes tumor invasion and metastasis in HNSCC.

Biochimica et biophysica acta. Molecular basis of disease·2026
Same author

Artificial Intelligence Chatbots' Performance on Dental Trauma Case-based Queries: Examining the Effect of Prompt and Content Engineering.

Journal of endodontics·2026
Same author

Comparative analysis of the dental plaque metabolome in tooth stain and caries within primary dentition.

BMC oral health·2026
Same author

Plant-Derived Nanovesicles: Resolving Conceptual Confusion, Overcoming Isolation Challenges, and Advancing Translational Potential.

International journal of nanomedicine·2026
Same author

Stability Challenges and Engineering Strategies of Plant-Derived Extracellular Vesicle-Like Particles: A Translational Perspective.

International journal of nanomedicine·2026
Same author

Kynurenine promotes angiogenesis through mTOR signaling in head and neck squamous cell carcinoma.

Scientific reports·2026

Related Experiment Video

Updated: May 28, 2025

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

1.7K

Machine learning models for prognosis prediction in regenerative endodontic procedures.

Jing Lu1, Qianqian Cai2, Kaizhi Chen2

  • 1Fujian Key Laboratory of Oral Diseases, School and Hospital of Stomatology, Fujian Medical University, Fuzhou, China.

BMC Oral Health
|February 13, 2025
PubMed
Summary
This summary is machine-generated.

Machine learning models, including Random Forest (RF) and Gradient Boosting Machine (GBM), accurately predict regenerative endodontic procedure (REP) outcomes. Feature importance analysis aids in developing prognosis scoring systems for clinical decision-making.

Keywords:
Machine learningPrognosis predictionRegenerative endodontic procedures

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.3K

Related Experiment Videos

Last Updated: May 28, 2025

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

1.7K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K
Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities
07:14

Guided Endodontics: Three-Dimensional Planning and Template-Aided Preparation of Endodontic Access Cavities

Published on: May 24, 2022

4.3K

Area of Science:

  • Endodontics
  • Biomedical Engineering
  • Machine Learning in Healthcare

Background:

  • Regenerative endodontic procedures (REPs) aim to restore immature teeth with pulp necrosis.
  • Predicting REP success is crucial for clinical decision-making and avoiding treatment failure.
  • Machine learning (ML) offers potential for developing predictive models in endodontics.

Purpose of the Study:

  • To establish and validate ML models for predicting the clinical prognosis of REPs.
  • To assist clinicians in making informed decisions and improving treatment outcomes.
  • To identify key factors influencing REP success.

Main Methods:

  • Radiographic examination and measurement of 268 teeth from 198 patients.
  • Implementation of five ML models: RF, GBM, XGB, logR, and SVM.
  • Cross-validation using a stratified five-fold approach with 8:2 training/test split.
  • Feature importance analysis and calculation of seven performance metrics (AUC, accuracy, F1-score, etc.).

Main Results:

  • RF and GBM models demonstrated superior performance in predicting 1-year and 2-year REP outcomes (e.g., RF Accuracy=0.91, AUC=0.94 for 1-year).
  • Key predictors identified include age, sex, etiology, root canal number, trauma type, periapical lesion size, and root development stage.
  • Feature importance ranking provides insights into factors influencing treatment success.

Conclusions:

  • RF and GBM models show significant potential for predicting REP prognosis, outperforming other tested ML models.
  • The identified feature importance ranking can contribute to a scoring system for REP prognosis.
  • These ML models can aid clinicians in decision-making for regenerative endodontics.