Evidence map›Paper›PMID 42151338›Full record

ArticleNPJ digital medicine2026

Prospective deployment of AI-based risk stratification to enable expedited mammography workflow in a safety-net setting.

Maggie Chung, Eric Davis, Heather Greenwood, Jessica Hayward, Shinn-Huey Shirley Chou, Bonnie Joe, Loretta Strachowski, Tatiana Kelil, Rita Freimanis, Elissa Price and 3 more

Abstract read
PubMed Full text at PMC Publisher
In one paragraph

Article in NPJ digital medicine, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.

0numbers the graph read from it
0cells of the map it votes in
0citing papers in PubMed
–field-weighted citation impact
1 · What the graph read from it

What it found

Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.

The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.

2 · The registry

The trial behind it

Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.

Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.

3 · Its place in the literature

Who cites it

0 citing papers in PubMed.

No citing paper in PubMed yet.

4 · The record

Corrections and comments

PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.

5 · Who and what money

Authors and funding

13 authors.

Maggie ChungDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA. Maggie.chung@ucsf.edu.
Eric DavisDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Heather GreenwoodDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Jessica HaywardDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Shinn-Huey Shirley ChouDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Bonnie JoeDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Loretta StrachowskiDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Tatiana KelilDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Rita FreimanisDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Elissa PriceDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Kimberly RayDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Amie LeeDepartment of Radiology and Biomedical Imaging, University of California, San Francisco, CA, USA.
Adam YalaComputational Precision Health, University of California, Berkeley and University of California, San Francisco, Berkeley, CA, USA.

Funding

Pillar: Multi-Modal Imaging AI Models for Breast Cancer RiskR37CA289821 · NCI · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · PI Maggie Chung, Adam Yala · 2025 to 2026
$1.2M
NCI NIH HHS R37 CA289821NIH HHS R37 CA289821
6 · The paper itself

Abstract

Delays between screening and diagnostic mammography contribute to disparities in breast cancer outcomes and reduce screening adherence. We prospectively evaluated the operational feasibility and impact of integrating AI risk stratification into screening workflows at an urban safety net facility. In this HIPAA-compliant, IRB-approved, controlled study, Mirai 1-year risk scores were generated in real time from screening mammograms. Patients in the top 10% of risk were flagged as high-risk and, on enrollment days, were offered immediate screening interpretation and same-day diagnostic evaluation when indicated. Outcomes included operational feasibility, care delivery timelines for screening results, diagnostic evaluation, and biopsy, and cancer detection rate, compared with high-risk controls on non-enrollment days. Among 4145 screening mammograms, 525 were flagged as high-risk and 100 women consented to expedited care, of whom 94 percent received immediate reads and 26 received same-day diagnostic evaluation. Time to screening results, diagnostic evaluation, and biopsy were significantly shorter in expedited patients versus control patients with screen-detected cancers, with reductions of 99.1%, 99.1%, and 87.2%, respectively. The expedited cohort demonstrated a cancer detection rate of 60/1000 compared with 2.3/1000 among non-high-risk participants. Integrating AI risk models into clinical workflows substantially improved care delivery timelines and provides a translational framework to improve care and reduce disparities.

Identifiers

PMID42151338
PMCPMC13448717

What OpenQuestion holds

Textmetadata
LicenceCC BY
Read underepoch 390

Registered trials

None linked

Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.