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

A wearable PEDTM/rGO/AuNPs non-enzymatic sensor integrated with nanofiber microfluidic chip for sweat collection and continuous glucose monitoring.

Mikrochimica acta·2026
Same author

Traditional Chinese Medicine Bone-Setting Techniques Research Progress for the Treatment of Knee Osteoarthritis.

BioMed research international·2026
Same author

Visual field progression in varying severities of treated patients with primary angle closure glaucoma.

Scientific reports·2026
Same author

Polygenic Risk Scores for Myopia: A Systematic Review of Predictive Performance and Clinical Potential.

Ophthalmic & physiological optics : the journal of the British College of Ophthalmic Opticians (Optometrists)·2026
Same author

A bibliometric and visualization analysis of global trends and emerging themes in acetylation research for lung cancer.

Discover oncology·2026
Same author

DWGCN: distance-weighted graph convolutional network for robust spatial domain identification in spatial transcriptomics.

Frontiers in genetics·2026

Related Experiment Video

Updated: May 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K

Use of deep learning model for paediatric elbow radiograph binomial classification: initial experience, performance

Mark Bangwei Tan1, Yuezhi Russ Chua2, Qiao Fan3

  • 1Department of Diagnostic Radiology, Singapore General Hospital, Singapore.

Singapore Medical Journal
|April 21, 2025
PubMed
Summary

A deep learning model using convolutional neural networks (CNNs) demonstrated higher sensitivity in classifying paediatric elbow radiographs compared to emergency department physicians. This artificial intelligence (AI) tool shows promise for improving diagnostic accuracy in paediatric radiology.

Keywords:
Artificial intelligenceemergency radiologymachine learningmusculoskeletal radiologypaediatric radiology

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
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

Related Experiment Videos

Last Updated: May 12, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.6K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.6K
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

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Paediatric elbow fractures are common, requiring accurate radiographic interpretation.
  • Emergency department physicians face challenges in interpreting these images, potentially leading to diagnostic delays or errors.

Purpose of the Study:

  • To compare the diagnostic performance of a CNN-based AI model against paediatric emergency department physicians for classifying paediatric elbow radiographs.
  • To evaluate the accuracy, sensitivity, and specificity of the AI model in detecting abnormalities in paediatric elbow X-rays.

Main Methods:

  • A dataset of 1,314 paediatric elbow lateral radiographs was curated and classified as normal or abnormal.
  • A CNN model (EfficientNet B1) was trained on a development set and validated.
  • The AI model's performance was evaluated on a test set and compared to five physicians using McNemar test.

Main Results:

  • The AI model achieved an accuracy of 80.4% and an AUROC of 0.872 on the test set.
  • The AI model demonstrated higher sensitivity (79.0%) compared to physicians (64.9%), though not statistically significant (P = 0.088).
  • Physician specificity was higher (87.3%) than the AI model (81.8%), also not statistically significant (P = 0.439).

Conclusions:

  • The AI model exhibited strong performance with good AUROC values and superior sensitivity compared to the physician group.
  • The findings suggest that AI can be a valuable tool to assist clinicians in diagnosing paediatric elbow abnormalities.
  • Further research is warranted to optimize AI models and integrate them into clinical workflows for improved paediatric care.