65 Quick summary: A retrospective Swedish study has revealed that three commercially available radiology artificial intelligence systems can successfully flag mammographic signs of breast cancer up to six years before a formal clinical diagnosis. The systems achieved 90% specificity by identifying early elevated risk scores in approximately 20% of future cancer cases, demonstrating a strong predictive capacity that increases as the date of diagnosis approaches. Integrating these advanced diagnostic tools into healthcare practice and public policy frameworks could significantly improve early intervention strategies, thereby reducing mortality rates and enhancing the long-term psychological well-being of patients through personalised screening vigilance. Three commercially available radiology AI systems have shown the potential to flag early signs of breast cancer up to six years before a diagnosis, according to a study published in Radiology, the flagship journal of the Radiological Society of North America. In a Swedish retrospective study, researchers tested three AI-based computer-assisted detection (AI-CAD) systems on mammogram data from a large screening population. They found that cancer prediction scores issued by AI-CAD were elevated, on average, for individuals who were eventually diagnosed with breast cancer, while scores were low for those who remained cancer-free. “Approximately 20% of breast cancer cases demonstrate mammographic signs that are already visible to AI around six years before diagnosis,” said senior co-author Fredrik Strand, MD, of Karolinska University Hospital in 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.” The researchers included a total of 88,963 mammograms performed on 31,394 patients across a period of 10 years. Data were taken from the Validation of Artificial Intelligence for Breast Imaging (VAI-B) database, which collects breast imaging data from volunteers across four regions of Sweden. The Swedish national breast screening programme invites women between the ages of 40 and 74 to screening examinations every two years, with each mammogram traditionally read by two radiologists. The three AI-CAD systems were applied to mammograms taken between January 2008 and April 2019. Across that period, 12,072 of the participants, or 38.5%, were diagnosed with cancer by radiologist readers. The systems successfully identified many of those cancers at earlier screening points, achieving 90% specificity in up to 19.7% of individuals 6 years before their recorded diagnosis, up to 25.2% in 4 years before diagnosis, and up to 39.3% two years before diagnosis. The researchers say AI-CAD scores could help radiologists spot early mammographic signs of potential future cancers, and that a personalised approach to interpreting individual scores could help identify patients who might benefit from closer vigilance. “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 Dr Strand. “Analysing the AI scores of screened individuals over time could provide insight into how early detectable changes arise, potentially allowing for earlier intervention.” As a retrospective analysis, the work demonstrates potential rather than real-time clinical performance. Prospective trials will be essential to determine how AI alerts could be integrated safely into existing workflows without increasing unnecessary recalls or anxiety. Dr Strand and colleagues emphasise that AI should complement, not replace, radiologist expertise. The study, titled “Artificial Intelligence Detection Scores in Screening Mammography for Early Breast Cancer Alerts,” was published online on 9th June 2026.