AI Systems Can Potentially Flag Breast Cancer Years Before Diagnosis

TUESDAY, June 16, 2026 (HealthDay News) — Three commercially available artificial intelligence (AI) systems show potential for flagging early signs of breast cancer years before a diagnosis, according to a study published online June 9 in Radiology.

Sarah Hickman, M.D., Ph.D., from Barts Health NHS Trust in London, and colleagues conducted a retrospective study using the Validation of Artificial Intelligence for Breast Imaging database covering four regions in Sweden from January 2008 to April 2019 to demonstrate how AI scores in individuals diagnosed with breast cancer may increase up to 10 years before diagnosis. Raw examination-level AI scores were provided by three AI computer-aided detection systems (AI-1, AI-2, and AI-3).

A total of 31,394 individuals with 88,963 examinations were included; 38.5 percent were diagnosed with cancer. The researchers found that the proportion of cancers potentially flagged at 90 percent specificity was 12.7, 13.8, and 17.0 percent by AI-1, AI-2, and AI-3, respectively, at 10 years before diagnosis; 19.0, 19.6, and 19.7 percent, respectively, at six years before diagnosis; and 24.2, 23.3, and 25.2 percent, respectively, at four years before diagnosis. Excluding screen detection, the area under the receiver operating characteristic curve (AUC) ranged from 0.63 to 0.67 for the three AI computer-aided detection systems for all time points combined compared with an AUC of 0.57 for mammographic density.

“Our study confirms the potential of AI to, in some cases, find signs of cancer in the mammograms much earlier than when radiologists detected it,” senior author Fredrik Strand, M.D., Ph.D., from the Karolinska University Hospital in Stockholm, said in a statement.

Two authors hold stock in ClearScanAI.

Abstract/Full Text