A Trial Comparing Screening Mammography With and Without Assistance From Artificial Intelligence for Breast Cancer Detection and Recall Rates in Adult Patients (PRISM)

A Randomized Controlled Trial Comparing Screening Mammography With and Without Assistance From Artificial Intelligence for Breast Cancer Detection and Recall Rates in Adult Patients

The goal of this clinical trial is to compare patient-centered outcomes when screening digital breast tomosynthesis (DBT) exams are interpreted with versus without a leading FDA-cleared artificial intelligence (AI) decision-support tool in real-world U.S. settings and to assess patients' and radiologists' perspectives on AI in medicine.

The main question it aims to answer is: Does an FDA-cleared AI decision-support tool for digital tomosynthesis (DBT) improve screening outcomes in real world US clinical settings?

This trial will include all interpreting radiologists and all adult patients undergoing screening mammography at any of the participating breast imaging facilities across 6 regional health systems (University of California, Los Angeles (UCLA), University of California, San Diego (UCSD), University of Washington-Seattle, University of Wisconsin-Madison, Boston Medical Center, and University of Miami) during the trial period.

All screening mammograms at these facilities will be randomized to either intervention (radiologist assisted by an AI decision support tool) versus usual care (radiologist alone) to see if interpreting these mammograms with the AI tool's assistance improves patient screening outcomes.

We are targeting 400,000 screening exams across the participating health systems in this trial.

Study Overview

• Status: Recruiting
• Conditions: Breast Cancer Screening; Artificial Intelligence (AI)
• Intervention / Treatment: Device: Artificial intelligence (AI) decision-support tool

Detailed Description

During the RCT the AI support tool will be randomized to be turned on or off (1:1) at the mammography exam level. Patients who return for screening exams in year 2 of recruitment will be randomized again (e.g., they will not retain their prior randomization). Radiologists will not be able to sort exams based on AI availability or AI scores. Randomizing by exam level will ensure that we capture a substantial number of interpretations with vs. without AI for each radiologist, allowing for quantification of the radiologist-level AI learning curve. We are not randomizing at the facility level as some radiologists interpret exams acquired at different facilities on the same day. By randomizing AI at the exam level, we will have the best ability to estimate and adjust for temporal trends in screening outcomes across individual radiologists. Randomization across large regional health systems will be managed independently at each participating site.

Our RCT randomizes screening mammography exams to be interpreted either with or without an AI decision-support tool. As a result, radiologists cannot be blinded to study arm during screening mammography interpretation. However, interpreting radiologists and facility staff (e.g., those scheduling the exams) will not know in advance which patients will be randomized to the AI tool. Randomization occurs within minutes after the breast imaging acquisition (i.e., when the mammography technologist captures the images) by an automated system that was developed by a third-party AI platform and successfully piloted at UCLA. Thus, the AI data (or lack thereof) is embedded within the mammogram before the radiologist opens the exam, preventing any option to "add AI" to an exam randomized to be interpreted without AI. Radiologists will be aware of AI availability only at the time of interpretation, as AI information will appear upon opening the exam (e.g., the AI information pops up with the exam images).

• Study Type: Interventional
• Enrollment (Estimated): 400000
• Phase: Phase 4

Contacts and Locations

• Study Contact: Name: Michelle L'Hommedieu, PhD; Phone Number: (310) 592-9454; Email: mlhommedieu@mednet.ucla.edu

Study Locations

• United States
  • California
    • Los Angeles, California, United States, 90024
      • Recruiting
      • University of California Los Angeles Health System
      • Principal Investigator: Hannah S. Milch, MD
      • Contact: Michelle L'Hommedieu, PhD; Phone Number: (310) 592-9454; Email: mlhommedieu@mednet.ucla.edu
      • Principal Investigator: Joann G Elmore, MD, MPH
    • San Diego, California, United States, 92093
      • Recruiting
      • University of California, San Diego
      • Principal Investigator: Haydee Ojeda-Fournier, MD
      • Contact: Haydee Ojeda-Fournier, MD; Phone Number: (858) 442-1902; Email: hojeda@health.ucsd.edu
  • Florida
    • Miami, Florida, United States, 33136
      • Recruiting
      • University of Miami Health System
      • Contact: Jose Net, MD; Phone Number: (305) 215-0461; Email: jnet@med.miami.edu
      • Principal Investigator: Jose Net, MD
  • Massachusetts
    • Boston, Massachusetts, United States, 02118
      • Recruiting
      • Boston Medical Center
      • Contact: Clare Poynton, MD, PhD; Phone Number: (617) 638-6626; Email: clare.poynton@bmc.org
      • Principal Investigator: Clare Poynton, MD, PhD
  • Washington
    • Seattle, Washington, United States, 98195
      • Recruiting
      • University of Washington Health System
      • Contact: Janie Lee, MD, MSc; Phone Number: (206) 606-6241; Email: jmlee58@fredhutch.org
      • Principal Investigator: Janie Lee, MD, MSc
  • Wisconsin
    • Madison, Wisconsin, United States, 53706
      • Recruiting
      • University of Wisconsin-Madison
      • Contact: Christoph Lee, MD, MSc; Phone Number: (608) 263-9377; Email: cilee3@uwhealth.org
      • Principal Investigator: Christoph Lee, MD, MSc

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

This trial will include all radiologists interpreting screening mammography and all adult patients undergoing screening mammography at any of the participating breast imaging facilities across 6 regional health systems (UCLA, UC San Diego, University of Washington-Seattle, University of Wisconsin-Madison, Boston Medical Center, and University of Miami) during the trial period. Individuals must meet the following eligiblity criteria.

Inclusion Criteria:

1. Be at least 18 years of age or older
2. Receive a screening mammogram at one of the participating breast imaging facilities OR be a radiologist who interprets screening mammograms at one of the participating breast imaging facilities.

Exclusion Criteria:

1. Patients who have opted out of all research at the health system

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
No Intervention: Standard care (radiologist alone); 3D screening exams randomized to this arm will be interpreted in accordance with standard care (i.e., interpreted by the radiologist alone, without an AI decision-support tool's assistance).
Active Comparator: Intervention (radiologist assisted by AI); 3D screening exams randomized to this arm will be interpreted by the radiologist assisted by the AI decision-support tool (i.e., intervention).	Device: Artificial intelligence (AI) decision-support tool; The intervention is an AI decision-support tool to help radiologists interpret 3D screening mammograms. For exams randomized to this intervention arm, the first image displayed to the radiologist upon opening an exam on the viewing station will be a one-page, standardized AI report showing the overall exam risk (elevated, intermediate, or low), image region markings, lesion scores from 1-100 (100 being the highest suspicion), bounding boxes, and relevant slice locations for 3D exams. Radiologists can toggle markings on/off and retain full control over the final interpretation of the exam as positive or negative (i.e., they can choose to ignore the AI information). Randomization occurs 1:1 at the exam level via automated code at image acquisition. Returning patients in year two will be re-randomized. Radiologists cannot filter their exam lists by AI availability or risk, and randomization will be independently managed at each participating health system.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Cancer detection rate	Number of screening exams recommended for breast biopsy (final Breast Imaging- Reporting and Data System [BI-RADS] assessment of 4 or 5) resulting in detected cancer, per 1,000 screening exams	Cancer diagnosed within 90 days of positive study entry screening mammogram
Recall rate	Number of screening exams recalled for diagnostic work-up (initial BI-RADS assessment of 0, 3, 4, or 5), per 1,000 screening exams	Through study completion, an average of 1 year

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Interval cancer rate (i.e., false-negative rate)	Number of screening exams with a negative assessment (final BI-RADS assessment of 1 or 2) and breast cancer diagnosed within 1 year, per 1,000 screening exams	Cancer diagnosed within 365 days of a negative study entry screening mammogram
False positive recall rate	Proportion of screening exams recalled for additional imaging (final BI-RADS assessment of 1, 2, or 3), with no breast cancer diagnosed within 1 year	No cancer diagnosed within 365 days of a positive study entry screening mammogram
False positive short-interval follow-up recommendation rate	Proportion of screening exams recalled for short-interval follow-up (final BI-RADS assessment of 3) with no breast cancer diagnosed within 1 year	No cancer diagnosed within 365 days of a positive study entry screening mammogram
False positive biopsy recommendation rate	Proportion of screening exams recalled for breast biopsy (final BI-RADS assessment of 4 or 5) with no breast cancer diagnosed within 1 year	No cancer diagnosed within 365 days of a positive study entry screening mammogram
Trust and confidence in AI	Trust and confidence in AI gathered from focus group and survey data	Years 1,2 and Years 4,5
Efficiency metrics (only for the UCLA site)	Interpretation time required for radiologists to interpret each mammogram with versus without AI. Delivery time, using time stamp data from exam acquisition to delivery of results to patients (aka turnaround time).	Through study completion, an average of 1 year

Collaborators and Investigators

• Sponsor: Jonsson Comprehensive Cancer Center
• Collaborators: Patient-Centered Outcomes Research Institute; University of California, San Diego; University of California, Los Angeles; University of Miami; University of Wisconsin, Madison; Boston Medical Center; University of California, Davis; University of Washington; California Breast Cancer Research Program
• Investigators: Principal Investigator: Diana Miglioretti, PhD, University of California, Davis; Principal Investigator: Joann G Elmore, MD, MPH, University of California, Los Angeles

Study record dates

Study Major Dates

• Study Start (Actual): October 15, 2025
• Primary Completion (Estimated): March 1, 2028
• Study Completion (Estimated): March 1, 2030

Study Registration Dates

• First Submitted: April 11, 2025
• First Submitted That Met QC Criteria: April 11, 2025
• First Posted (Actual): April 18, 2025

Study Record Updates

• Last Update Posted (Actual): November 26, 2025
• Last Update Submitted That Met QC Criteria: November 24, 2025
• Last Verified: October 1, 2025

More Information

Terms related to this study

• Keywords: Breast cancer screening; Artificial intelligence (AI)
• Additional Relevant MeSH Terms: Neoplasms by Site; Neoplasms; Skin Diseases; Breast Diseases; Breast Neoplasms
• Other Study ID Numbers: 24-1192; 1R01CA288824-01A1 (U.S. NIH Grant/Contract)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: A de-identified dataset from this study will be deposited in the Patient-Centered Outcomes Data Repository (PCODR) housed at the Inter-university Consortium for Political and Social Research (ICPSR) at the University of Michigan, in compliance with PCORI's Policy on Data Management and Data Sharing.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: Yes
• product manufactured in and exported from the U.S.: No