An official website of the United States government
Government Funding Lapse Because of a lapse in government funding, the information on this website may not be up to date, transactions submitted via the website may not be processed, and the agency may not be able to respond to inquiries until appropriations are enacted.
The NIH Clinical Center (the research hospital of NIH) is open. For more details about its operating status, please visit cc.nih.gov.
Updates regarding government operating status and resumption of normal operations can be found at opm.gov.
Artificial Intelligence Intervention for Improving Interpretation of Screening Mammography
Trial Status: approved
This clinical trial tests an artificial intelligence (AI) decision-support tool for improving interpretation of screening mammograms. Over 40 million women receive mammograms each year to screen for breast cancer. Computer-aided detection (CAD) tools for screening mammography were initially developed in the late 1990s to support and improve imperfect interpretation by radiologists. Unfortunately, these tools were found to be associated with lower diagnostic accuracy, increased patient harms, and excess medical costs after clinical implementation. AI may help radiologists provide more accurate results to patients by identifying areas of concern on some mammograms and providing further confidence on identifying negative exams. Information gathered from this study may help researchers learn whether an AI decision-support tool may be improve interpretation of screening mammograms.
Inclusion Criteria
RADIOLOGIST COHORT: All radiologists who interpret screening mammograms at University of California, Los Angeles (UCLA) or University of Washington breast imaging facilities over an approximate 24-month time frame. Additional sites to be named.
PATIENT COHORT: All adults presenting for screening mammography at UCLA or University of Washington breast imaging facilities over a 24-month time period. Additional sites to be named.
Additional locations may be listed on ClinicalTrials.gov for NCT06934239.
I. Conduct a 2-year randomized controlled trial (RCT) and assess immediate performance measures and outcomes of the diagnostic evaluation cascade for three-dimensional (3D) screening mammograms interpreted with versus (vs.) without AI.
II. Assess 1-year breast cancer performance measures and clinical patient outcomes for 3D screening mammograms interpreted with vs. without AI.
III. Will perform subgroup analyses of the interaction of patient-, exam-, and radiologist-level characteristics associated with improved screening performance with AI.
OUTLINE: Participants are randomized to 1 of 2 arms.
ARM I: Participants interpret screening mammograms and issue a final interpretation with AI decision-support tool on study.
ARM II: Participants undergo interpret screening mammograms and issue a final interpretation per standard of care (SOC) on study.
After completion of study intervention, participants are followed up at 1 year.
Trial PhaseNo phase specified
Trial Typescreening
Lead OrganizationUCLA / Jonsson Comprehensive Cancer Center
