MONDAY, Nov. 3, 2025 (HealthDay News) -- Risk scores generated by a deep learning algorithm (Mirai) can identify women at higher risk for developing interval breast cancers (ICs), according to a study published online Oct. 28 in Radiology.Joshua W.D. Rothwell, from the University of Cambridge School of Clinical Medicine in the United Kingdom, and colleagues examined the predictive ability of three-year risk scores generated by Mirai to identify women who developed ICs in the U.K. breast screening program. Digital screening mammograms with negative results collected from a three-year cohort were processed by Mirai.The analysis included 134,217 examinations from the same number of women and included 524 ICs. No evidence was seen for performance differences among one-, two-, and three-year IC predictions, age quartiles, or breast densities. For one-, two-, and three-year IC predictions, the areas under the receiver operating characteristic curves were 0.72, 0.67, and 0.67, respectively. For age quartiles, C-indexes were 0.67, 0.70, 0.71, and 0.71 for those younger than 52, 52 to 58, 59 to 65, and 66 years and older, respectively. For Breast Imaging Reporting and Data System categories a, b, c, and d, C indexes were 0.70, 0.69, 0.68, and 0.67, respectively. For women assigned the highest 1, 5, 10, and 20 percent of scores, three-year risk scores retrospectively predicted 3.6, 14.5, 26.1, and 42.4 percent of ICs, respectively."Further workup of mammograms within the top 20 percent of scores could yield 42.4 percent of interval cancers, meaning that Mirai could be used to identify women for supplemental imaging or a shortened screening interval, instead of or in addition to breast density," Rothwell said in a statement.Several authors disclosed ties to the biopharmaceutical and medical device industries.Abstract/Full TextEditorial (subscription or payment may be required).Sign up for our weekly HealthDay newsletter