AI Tool for Breast Cancer Screening

(PRISM Trial)

Recruiting at 5 trial locations

Overseen By Michelle L'Hommedieu, PhD

Age: 18+

Sex: Any

Trial Phase: Phase 4

Sponsor: Jonsson Comprehensive Cancer Center

Disqualifiers: Non-adult, Non-patient, Non-radiologist, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Prior Safety Data This treatment has passed at least one previous human trial

Compensation: Varies

Number of Visits: Unknown

400000 Participants Needed

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests whether an FDA-approved artificial intelligence (AI) tool can help radiologists improve breast cancer screening outcomes. It examines the interpretation of mammograms (breast X-rays), comparing results with and without the AI tool's assistance. The trial focuses on understanding the benefits of using AI in real-world settings and gathering feedback from patients and doctors. Patients receiving a screening mammogram at one of the six participating medical centers might be part of this study. As a Phase 4 trial, this research emphasizes that the AI tool is already FDA-approved and proven effective, aiming to understand how it can benefit more patients.

Will I have to stop taking my current medications?

The trial information does not specify whether participants need to stop taking their current medications.

What is the safety track record for the AI decision-support tool?

Research has shown that the AI tool used for breast cancer screening is safe. The FDA has approved it, indicating it has passed important safety checks. In earlier studies, doctors using this AI tool detected more cases of breast cancer than when working without it, demonstrating its effectiveness in aiding early cancer detection.

No major problems have been reported with using AI in breast cancer screening. The tool assists radiologists without replacing them, ensuring no direct risk to patients. Overall, the AI tool is safe and effective in helping to read mammograms. ^{1 2 3 4 5}

Why are researchers enthusiastic about this study treatment?

Researchers are excited about using an AI decision-support tool for breast cancer screening because it could enhance the accuracy and efficiency of interpreting 3D mammograms. Unlike the standard approach where radiologists work alone, this AI-assisted method helps in identifying subtle patterns and abnormalities that might be missed by human eyes alone. The AI tool aims to reduce false positives and negatives, potentially leading to earlier detection and improved outcomes for patients. This innovative approach could set a new benchmark for precision in breast cancer diagnostics.

What evidence suggests that this AI tool is effective for breast cancer screening?

This trial will compare standard care, where a radiologist alone interprets 3D screening exams, with an intervention where an AI decision-support tool assists the radiologist. Studies have shown that AI tools can enhance breast cancer screening. Research indicates that AI often matches or surpasses human radiologists in diagnosing breast cancer. In some cases, combining AI with a radiologist has led to detecting more breast cancers than using two human experts alone. Additionally, AI can improve screening programs cost-effectively by better identifying individuals at higher risk. These findings suggest that AI can be a valuable tool in enhancing breast cancer detection and screening outcomes. ^{3 6 7 8 9}

Who Is on the Research Team?

Joann G Elmore, MD, MPH

Principal Investigator

University of California, Los Angeles

Diana Miglioretti, PhD

Principal Investigator

University of California, Davis

Are You a Good Fit for This Trial?

This trial is for all adult patients getting 3D mammography breast cancer screenings at UCLA and UW health systems. It includes radiologists interpreting these screenings. There are no specific inclusion or exclusion criteria provided, suggesting it's a broad study.

Inclusion Criteria

I am an adult getting a 3D mammogram at UCLA or UW.

I am a radiologist who interprets breast cancer screenings at a specified facility.

Exclusion Criteria

Is neither an adult patient undergoing 3D mammography breast cancer screening at any of the 16 imaging facilities across UCLA and UW health systems

I am a radiologist who interprets breast cancer screenings at a specified facility.

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Randomized Controlled Trial

3D screening mammograms are interpreted with versus without AI to assess immediate performance measures and outcomes

2 years

Regular visits as per mammography schedule

Follow-up

Participants are monitored for longer-term performance measures and clinical patient outcomes

1 year

Subgroup Analysis

Analysis of patient-, exam-, and radiologist-level characteristics associated with improved screening performance with AI

Concurrent with main trial

What Are the Treatments Tested in This Trial?

Interventions

• Artificial intelligence (AI) decision-support tool

Trial Overview The trial tests if using an FDA-cleared AI tool to help read 3D mammograms improves detection of breast cancer and affects the recall rate after initial use. It also examines if outcomes differ based on patient demographics or radiologist experience.

How Is the Trial Designed?

Group I: Standard care (radiologist alone) Active Control 1 Intervention

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).

Group II: Intervention (radiologist assisted by AI) Active Control 1 Intervention

3D screening exams randomized to this arm will be interpreted by the radiologist assisted by the AI decision-support tool (i.e., intervention).

Who Is Running the Clinical Trial?

Jonsson Comprehensive Cancer Center

Lead Sponsor

Trials

373

Recruited

35,200+

National Cancer Institute (NCI)

Collaborator

Trials

14,080

Recruited

41,180,000+

University of California, Los Angeles

Collaborator

Trials

1,594

Recruited

10,430,000+

National Institutes of Health (NIH)

Collaborator

Trials

2,896

Recruited

8,053,000+

University of California, San Diego

Collaborator

Trials

1,215

Recruited

1,593,000+

University of Wisconsin, Madison

Collaborator

Trials

1,249

Recruited

3,255,000+

California Breast Cancer Research Program

Collaborator

Trials

16

Recruited

4,500+

Boston Medical Center

Collaborator

Trials

410

Recruited

890,000+

University of Miami

Collaborator

Trials

976

Recruited

423,000+

Patient-Centered Outcomes Research Institute

Collaborator

Trials

592

Recruited

27,110,000+

Published Research Related to This Trial

A multidisciplinary expert group identified key signals that a new AI system should emit to enhance the management of adverse drug events (ADEs) in patients taking oral antineoplastic agents, including educational reminders for patients and alerts for necessary tests and examinations.

In a 6-month observational study at a university hospital, a total of 3,641 ADEs were reported, highlighting the importance of patient education and clinical monitoring in improving patient safety and quality of life.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Analysis of adverse drug events as a way to improve cancer patient care. Vicente-Oliveros, N., Gramage-Caro, T., Corral de la Fuente, E., et al.[2022]

AI has the potential to enhance the processing and evaluation of Individual Case Safety Reports (ICSRs) in pharmacovigilance, as explored by the FDA, but current algorithms still require human oversight to ensure quality.

To fully leverage AI in pharmacovigilance, several challenges must be addressed, including the need for quality assurance, large training datasets, and the development of best practices and regulatory frameworks for implementation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

"Artificial Intelligence" for Pharmacovigilance: Ready for Prime Time? Ball, R., Dal Pan, G.[2023]

A machine-learning model was developed using data from 4638 patients across 16 FDA-approved small molecule kinase inhibitors (SMKIs) to analyze the relationship between kinase targets and adverse events (AEs), providing a new tool for predicting safety risks in cancer treatments.

The model not only helps identify potential kinase-inhibitor adverse event pairs but also serves as a precision medicine tool to enhance patient safety by forecasting clinical safety signals and aiding in the development of safer SMKI therapies.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Decoding kinase-adverse event associations for small molecule kinase inhibitors. Gong, X., Hu, M., Liu, J., et al.[2022]

Citations

1. nature.com nature.com/articles/s41467-025-57469-3

Artificial intelligence for breast cancer screening in ... This study compares the diagnostic accuracy of breast radiologists with and without AI-based computer-aided detection (AI-CAD) for screening mammograms in a ...

2. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC11885569/

Artificial intelligence for breast cancer screening in ... In support, multiple retrospective studies found that AI's diagnostic accuracy was similar to or better than that of breast radiologists (BRs).

3. thelancet.com thelancet.com/journals/landig/article/PIIS2589-7500(25)00064-0/fulltext

AI as an independent second reader in detection of ... Evaluating screening mammograms with one human reader and AI leads to increased breast cancer detection compared with double human reading, ...

4. sciencedirect.com sciencedirect.com/science/article/pii/S0960977625005818

Artificial intelligence as treatment support in breast cancer In this narrative review, we recapitulate the available data on AI utilization in BC treatment by focusing on surgical therapy, radiation therapy, systemic and ...

5. jamanetwork.com jamanetwork.com/journals/jamanetworkopen/fullarticle/2823253

Cost-Effectiveness of AI for Risk-Stratified Breast Cancer ... These results suggest that AI-based risk stratified breast cancer screening programs may be more cost-effective screening programs, providing additional health ...

6. nature.com nature.com/articles/s41591-024-03408-6

Nationwide real-world implementation of AI for cancer ... Radiologists in the AI-supported screening group achieved a breast cancer detection rate of 6.7 per 1,000, which was 17.6% (95% confidence ...

7. pmc.ncbi.nlm.nih.gov pmc.ncbi.nlm.nih.gov/articles/PMC10625863/

Artificial Intelligence in Breast Cancer Diagnosis and ... The role of AI encompasses screening, diagnosis, staging, biomarker evaluation, prognostication, and therapeutic response prediction.

8. jamanetwork.com jamanetwork.com/journals/jamanetworkopen/fullarticle/2824353

Artificial Intelligence Algorithm for Subclinical Breast ... These findings suggest that commercial AI algorithms developed for breast cancer detection may identify women at high risk of a future breast ...

9. sciencedirect.com sciencedirect.com/science/article/pii/S2949916X24000732

Artificial intelligence for breast cancer: Implications for ... A key advantage of AI in breast cancer screening is its ability to efficiently detect tumor lesions within the vast array of images from healthy individuals, ...