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

Physicians and artificial intelligence diverge in evaluating large language models on real clinical cases.

NPJ digital medicine·2026
Same author

Sequential Plasmid Curing and Genome Editing in <i>Escherichia coli</i> Nissle 1917.

ACS synthetic biology·2026
Same author

Quantifying the community transmission of <i>Mycobacterium tuberculosis</i> in a rapidly growing Chinese city: a nine-year population-based genomic and spatial analysis.

Emerging microbes & infections·2026
Same author

Atomic Alignment in PbS Nanocrystal Superlattices with Compact Inorganic Ligands via Reversible Oriented Attachment of Nanocrystals.

Journal of the American Chemical Society·2026
Same author

Hazard-portfolio patterns in US food recall severity reveal transferable pathogen signals and firm-specific compliance signals.

Scientific reports·2026
Same author

Genomic landscape of the human vaginal microbiome is linked to host genetics and population of origin.

Nature genetics·2026

Related Experiment Video

Updated: Oct 1, 2025

Three-Dimensional Finger Motion Tracking during Needling: A Solution for the Kinematic Analysis of Acupuncture Manipulation
08:27

Three-Dimensional Finger Motion Tracking during Needling: A Solution for the Kinematic Analysis of Acupuncture Manipulation

Published on: October 28, 2021

2.9K

Machine learning for technical skill assessment in surgery: a systematic review.

Kyle Lam1, Junhong Chen1, Zeyu Wang1

  • 1Department of Surgery and Cancer, 10th Floor Queen Elizabeth the Queen Mother Building, St Mary's Hospital, Imperial College, London, W2 1NY, UK.

NPJ Digital Medicine
|March 4, 2022
PubMed
Summary
This summary is machine-generated.

Machine learning (ML) offers automated surgical skill assessment, using methods like Hidden Markov Models, Support Vector Machines, and Artificial Neural Networks. Future tools need to assess real-world surgery and provide clinically valuable feedback.

More Related Videos

Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.8K
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

8.4K

Related Experiment Videos

Last Updated: Oct 1, 2025

Three-Dimensional Finger Motion Tracking during Needling: A Solution for the Kinematic Analysis of Acupuncture Manipulation
08:27

Three-Dimensional Finger Motion Tracking during Needling: A Solution for the Kinematic Analysis of Acupuncture Manipulation

Published on: October 28, 2021

2.9K
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.8K
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

8.4K

Area of Science:

  • Medical Informatics
  • Surgical Education
  • Artificial Intelligence in Medicine

Background:

  • Objective surgical skill assessment is crucial but current methods are often biased and time-consuming.
  • Machine learning (ML) presents an opportunity for automated, rapid, and unbiased performance evaluation.
  • Systematic review of ML applications in surgical skill assessment is needed to identify techniques and challenges.

Purpose of the Study:

  • To systematically review and synthesize the literature on ML techniques used for technical surgical skill assessment.
  • To identify common ML methods, data types, and application areas in surgical skill assessment.
  • To highlight challenges and barriers hindering the advancement of ML in this field.

Main Methods:

  • A systematic literature search adhering to the PRISMA statement was conducted.
  • 66 studies were included from an initial retrieval of 1896 studies.
  • Analysis focused on ML techniques (HMM, SVM, ANN), data types (kinematic, video/image), and task settings (benchtop, simulator, real-life).

Main Results:

  • Hidden Markov Models (HMM), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) were the most prevalent ML methods.
  • Kinematic data was most commonly used (40/66 studies), followed by video/image data (19/66 studies).
  • High accuracy rates (>80%) were reported, though study variations exist; common barriers include focus on basic tasks and lack of standardized datasets.

Conclusions:

  • ML, utilizing methods like HMM, SVM, and ANN, shows significant potential for accurate and objective surgical skill assessment.
  • Future ML-based assessment tools should transition from basic tasks to real-life surgical scenarios.
  • Development of interpretable feedback mechanisms with clinical relevance is essential for surgeon adoption.