AI Risk Stratification Can ID High-Risk Women From Screening Mammograms

TUESDAY, June 9, 2026 (HealthDay News) — Artificial intelligence (AI) risk stratification generated from screening mammograms can identify women with a high risk for breast cancer, allowing expedited care, according to a study published online May 18 in npj Digital Medicine.

Maggie Chung, M.D., from the University of California, San Francisco, and colleagues examined the operational feasibility and impact of integrating AI risk stratification into screening workflows at an urban safety net facility. Mirai one-year risk scores were generated from screening mammograms in real time; patients in the top 10 percent of risk were identified as high-risk and were offered immediate screening interpretation and diagnostic evaluation on the same day when indicated.

The researchers found that 525 of 4,145 screening mammograms were flagged as high-risk. One hundred women consented to expedited care; 94 received immediate reads and 26 received same-day diagnostic evaluation. In expedited patients versus controls, time to screening results, diagnostic evaluation, and biopsy were significantly shorter, with reductions of 99.1, 99.1, and 87.2 percent, respectively. The cancer detection rate was 60/1,000 in the expedited cohort compared with 2.3/1,000 among non-high-risk patients.

“Right now, many women follow the same screening schedule but their individual risk can be very different,” Chung said in a statement. “AI risk assessment gives us the chance to identify the women most likely to benefit from expedited care and get them what they need.”

Two authors disclosed ties to Voio.

Abstract/Full Text