Breast cancer warning signs may show up years before diagnosis, and AI may be able to spot them.

A new study in the journal Radiology analyzed 88,963 mammograms performed over 10 years on more than 31,000 patients in Sweden. Researchers tested three commercially available AI-based computer-assisted detection, or AI-CAD, systems and found they could provide an “early alert” for breast cancer up to six years before diagnosis.

The findings showed that cancer prediction scores issued by AI-CAD were elevated, on average, for people who were eventually diagnosed with breast cancer, while scores were low for those who remained cancer-free.

“Approximately 20 percent of breast cancer cases demonstrate mammographic signs that are already visible to AI around six years before diagnosis,” said senior co-author Professor Fredrik Strand, of Karolinska University Hospital, Stockholm.

“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.”

Professor Strand’s team examined mammograms from volunteers aged 40 to 74 across Sweden. After the screening exams, two radiologists analyzed each mammogram. The screenings were scheduled every two years and were taken between 2008 and 2019.

The researchers said AI-based systems have already shown promise in predicting five-year breast cancer risk and identifying women at risk of “interval” cancers between regular screening mammograms. In this study, they looked at the systems’ ability to flag mammographic signs present up to 10 years in advance.

Across the study period, 12,072 participants, or 38.5 percent, were diagnosed with cancer by radiologist readers. The AI-CAD systems identified many of those cancers at earlier screening points.

At 90 percent specificity, the systems identified nearly 20 percent of participants six years before their recorded diagnosis, up to 25 percent four years before diagnosis and nearly 40 percent two years before diagnosis.

“This study aims to add to the growing literature regarding the application of AI in breast cancer screening and how it can help play a role in earlier detection of breast cancer,” said Strand.

“Analyzing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention.”

Read more from Good News Network.