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

Disease-Specific Improvements Predict Long-Term Global Quality of Life After Functional Rhinoplasty.

The Laryngoscope·2026
Same author

Do Surgical Trainees Impact Surgeon Robotic Learning Curves?

The American surgeon·2026
Same author

Clinician's Guide to Artificial Intelligence: Technical Foundations of Machine Learning.

The Medical clinics of North America·2026
Same author

Future perspectives of artificial intelligence in vascular surgery.

The Journal of cardiovascular surgery·2025
Same author

A Review on the Disease Risk and Contemporary Management of Peripheral Arterial Disease in the HIV Population.

Annals of vascular surgery·2025
Same author

Complex aortic repair in older adults.

Seminars in vascular surgery·2025

Related Experiment Video

Updated: Jul 12, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K

Bias in artificial intelligence in vascular surgery.

Zachary Tran1, Julianne Byun1, Ha Yeon Lee1

  • 1Department of Surgery, Division of Vascular Surgery, Linda University School of Medicine, 11175 Campus Street, Suite 21123, Loma Linda, CA 92350.

Seminars in Vascular Surgery
|October 20, 2023
PubMed
Summary

Artificial intelligence (AI) transforms big data in patient care, but deep learning models face limitations. Addressing bias in AI algorithms is crucial for fair and transparent clinical applications.

Keywords:
Artificial intelligenceBiasBlack box

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

8.3K
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.7K

Related Experiment Videos

Last Updated: Jul 12, 2025

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions
06:18

Author Spotlight: Segmentation and VR for Advanced Neurovascular Interventions

Published on: April 5, 2024

1.1K
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

8.3K
Simulator Training for Endovascular Neurosurgery
08:08

Simulator Training for Endovascular Neurosurgery

Published on: May 6, 2020

3.7K

Area of Science:

  • Medical Informatics
  • Artificial Intelligence
  • Machine Learning

Background:

  • Artificial intelligence (AI) is revolutionizing big data utilization in patient care.
  • Deep learning models offer powerful analytical capabilities but require careful consideration of their limitations.
  • Bias in AI, from data collection to algorithm output, presents unique challenges in clinical settings.

Purpose of the Study:

  • To highlight the potential and limitations of AI, particularly deep learning, in patient care.
  • To discuss the challenges posed by various forms of bias in AI applications within healthcare.
  • To introduce algorithm fairness as a key area of research for mitigating AI bias.

Main Methods:

  • Reviewing the impact of bias across the AI lifecycle: data collection, algorithm development, and output review.
  • Exploring the principles and stages of algorithm fairness: preprocessing, optimization, and postprocessing.
  • Identifying key limitations including black box decision-making and data set disparities.

Main Results:

  • AI's application in patient care is significantly affected by inherent biases.
  • Algorithm fairness research aims to mitigate bias through systematic evaluation and optimization.
  • Current AI methodologies lack standardization, hindering transparency and trust.

Conclusions:

  • Recognizing and addressing AI limitations, such as biased data and lack of transparency, is essential for clinical adoption.
  • Ongoing research is necessary to ensure fairness, equity, and reliability in AI-driven healthcare.
  • Developing common reporting standards will enhance the transparency and trustworthiness of AI in patient care.