Factors such as age, family history, genetic background, and previous breast biopsies can be integrated into AI models to assess risk more effectively.
Artificial Intelligence (AI) is bringing a major transformation in the healthcare sector. One of its most promising applications is in the early and accurate detection of breast cancer, a disease where timely diagnosis often makes the difference between life and death.
Traditionally, mammograms — X-ray images of the breast — are used to detect cancer. However, according to the U.S. National Cancer Institute, mammograms fail to detect about 20% of breast cancers. To address this gap, researchers have been training AI systems to distinguish between normal and cancerous mammograms.
A large study in Sweden tested this approach by analyzing mammograms of more than 80,000 women. In this study, AI examined the scans of 50% of participants before radiologists reviewed them, while the remaining scans were analyzed by two radiologists. Remarkably, in the AI-assisted group, breast cancer was detected in 20% more women compared to the radiologist-only group.
Beyond diagnosis, AI shows potential to predict the risk of developing breast cancer within the next five years. Factors such as age, family history, genetic background, and previous breast biopsies can be integrated into AI models to assess risk more effectively. Researchers also believe AI could help guide treatment decisions — from identifying benign changes after diagnosis to evaluating how well chemotherapy is working before surgery.
Experts caution, however, that large-scale clinical trials are still needed to confirm the safety and reliability of AI systems. They also emphasize that the data used for training AI should be diverse and comprehensive to ensure accurate outcomes across populations.