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

Initial recruitment, diagnosis, conservative management, maternal and perinatal outcomes of hypertensive disorders of pregnancy.

AJOG global reports·2026
Same author

Aristotelia chilensis Fruit Extracts Exhibit Neuroprotective Properties Against Alzheimer's Disease Related Mechanisms.

Molecular neurobiology·2026
Same author

Taxonomic novelties and phylogenetic insights on Gilliesieae (Allioideae, Amaryllidaceae) from Chile.

PhytoKeys·2026
Same author

Resolving the taxonomic enigma of <i>Nesocaryum stylosum</i> (Boraginaceae): phylogenetic evidence for its reclassification as <i>Cryptantha stylosa</i>.

PhytoKeys·2026
Same author

Machine and deep learning models for ligament injury recognition: a systematic review and meta-analysis of imaging and novel diagnostic techniques.

EFORT open reviews·2026
Same author

Data-driven identification of metabolic and cardiovascular biomarkers in high-altitude workers: a machine learning approach.

Frontiers in public health·2025

Related Experiment Video

Updated: Aug 26, 2025

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

6.9K

Lateral elbow tendinopathy and artificial intelligence: Binary and multilabel findings detection using machine

Guillermo Droppelmann1,2,3, Manuel Tello4, Nicolás García5

  • 1Research Center on Medicine, Exercise, Sport and Health, MEDS Clinic, Santiago, RM, Chile.

Frontiers in Medicine
|October 10, 2022
PubMed
Summary

Machine learning models accurately detect degenerative findings and intrasubstance tears in ultrasound images for lateral elbow tendinopathy (LET). The random forest model demonstrated superior performance in both binary and multilabel classifications.

Keywords:
AUC curvediagnosisrandom foresttennis elbowultrasound

More Related Videos

Author Spotlight: Integrating Mechanical and Biological Analysis in Tendinopathy Research
04:37

Author Spotlight: Integrating Mechanical and Biological Analysis in Tendinopathy Research

Published on: March 1, 2024

930
Measuring Local Tissue Strains in Tendons via Open-Source Digital Image Correlation
07:50

Measuring Local Tissue Strains in Tendons via Open-Source Digital Image Correlation

Published on: January 27, 2023

2.2K

Related Experiment Videos

Last Updated: Aug 26, 2025

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

6.9K
Author Spotlight: Integrating Mechanical and Biological Analysis in Tendinopathy Research
04:37

Author Spotlight: Integrating Mechanical and Biological Analysis in Tendinopathy Research

Published on: March 1, 2024

930
Measuring Local Tissue Strains in Tendons via Open-Source Digital Image Correlation
07:50

Measuring Local Tissue Strains in Tendons via Open-Source Digital Image Correlation

Published on: January 27, 2023

2.2K

Area of Science:

  • Radiology
  • Medical Imaging
  • Machine Learning

Background:

  • Ultrasound (US) is crucial for identifying degenerative changes and intrasubstance tears in lateral elbow tendinopathy (LET).
  • Machine learning (ML) offers advanced support for radiological diagnosis in LET.

Purpose of the Study:

  • To evaluate the efficacy of multilabel classification models using ML for detecting degenerative findings and intrasubstance tears in US images of LET patients.
  • To compare the performance of various ML models in classifying specific tendon abnormalities.

Main Methods:

  • A retrospective analysis of 30,007 US images from 2,917 patients diagnosed with LET.
  • Implementation of six supervised ML models for binary and multilabel classification of four tendon findings: hypoechogenicity, neovascularity, enthesopathy, and intrasubstance tear.
  • Feature extraction included texture, intensity, and granularity patterns; performance was assessed using accuracy, sensitivity, specificity, and ROC analysis with 95% confidence intervals (CI).

Main Results:

  • The Random Forest (RF) model exhibited the highest performance across most metrics in binary classification.
  • RF achieved the best AUC (0.991) and sensitivity (0.775) for intrasubstance tears, while specificity was highest for hypoechogenicity (0.821).
  • In multilabel classification, RF yielded the highest accuracy (0.772), macro-average AUC (0.948), and micro-average AUC (0.962).

Conclusions:

  • ML algorithms applied to US images of LET demonstrate high diagnostic accuracy.
  • The RF model is particularly effective for both binary and multilabel classification of LET, especially for identifying intrasubstance tears.