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

Breast cancer risk prediction with artificial intelligence: promise, calibration, and clinical readiness.

Journal of the National Cancer Institute·2026
Same author

Local partisan context and mental health.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

WISDOM randomized trial comparing risk-based versus annual breast cancer screening: study cohort characteristics and design.

NPJ breast cancer·2026
Same author

Using Artificial Intelligence to Improve Timeliness of Follow-Up in Breast Cancer Screening.

Journal of the American College of Radiology : JACR·2026
Same author

Persistent Delays in Diagnostic Evaluation Timeliness After an Abnormal Screening Mammogram in the Years following the Onset of the COVID-19 Pandemic.

Academic radiology·2026
Same author

Outcomes of Density-Targeted Supplemental Breast Magnetic Resonance Imaging Screening by Breast Cancer Risk: Long-Term Health and Economic Considerations.

Annals of internal medicine·2026

Related Experiment Video

Updated: Sep 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

207

Radiologist Preferences for Artificial Intelligence-Based Decision Support During Screening Mammography

Nathaniel Hendrix1, Kathryn P Lowry2, Joann G Elmore3

  • 1Department of Global Health and Population, Harvard T.H. Chan School of Public Health, Boston, Massachusetts.

Journal of the American College of Radiology : JACR
|August 15, 2022
PubMed
Summary
This summary is machine-generated.

Radiologists prefer artificial intelligence (AI) for mammography when it balances cancer detection accuracy and integrates smoothly into workflows. Tailoring AI tools to user preferences is key for successful adoption in screening mammography.

Keywords:
Artificial intelligencebreast cancercancer screeningdiscrete choice experimentpreferences

More Related Videos

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

172

Related Experiment Videos

Last Updated: Sep 1, 2025

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

207
Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns
13:44

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

43.0K
Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence
08:05

Detection and Isolation of Cancer in Prostate Biopsies Using Stimulated Raman Histology and Artificial Intelligence

Published on: June 10, 2025

172

Area of Science:

  • Radiology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Oncology Decision Support

Background:

  • Artificial intelligence (AI) shows potential to enhance cancer detection and risk prediction in mammography screening.
  • Radiologists' specific preferences for AI tool characteristics and implementation remain largely unquantified.
  • Understanding these preferences is crucial for effective AI integration into clinical practice.

Purpose of the Study:

  • To determine how various attributes of AI-based cancer detection and risk prediction tools influence radiologists' intentions to use them during screening mammography.
  • To identify key features that drive or deter AI adoption among radiologists.

Main Methods:

  • Qualitative interviews identified essential AI attributes for breast cancer detection and risk prediction.
  • A discrete choice experiment was designed using these attributes, involving 150 US-based radiologists.
  • Radiologists made choices between hypothetical AI tools and standard screening; data analyzed using random parameters logit and latent class models.

Main Results:

  • Radiologists favored AI for cancer detection with balanced sensitivity/specificity (94% sensitivity, <25% exams marked) and end-of-protocol display.
  • For risk prediction, preferred AI models integrated both mammography images and clinical data.
  • Intended adoption rates ranged from 46% to 60%, with 26%-33% deterred by misaligned features.

Conclusions:

  • Most radiologists are open to using AI decision support tools in mammography.
  • Optimizing short-term AI uptake requires implementing tools that align with the preferences of potentially dissuadable users.
  • Addressing specific user preferences is critical for maximizing the impact of AI in mammography screening.