The study investigated the use of automated artificial intelligence (AI) for triage and decision support in mammography and digital tomosynthesis for breast cancer screening. This is a paired noninferiority study that compared AI with double reading by radiologists. The results showed that AI is no worse than double reading. AI-assisted detection of small tumors smaller than 20 mm (p=0.002), node-negative metastases (p=0.001), luminal A subtype (p=0.002), and low-grade invasive ductal carcinomas (p=0.009) increased significantly. AI resulted in approximately an 11% increase in the detection of invasive cancers and a 13% increase in the detection of ductal carcinoma in situ (DCIS). The study was published in Nature Medicine on March 19, 2026.[1]