Breast cancer is one of the most common cancers affecting women around the world. Many countries have screening programs that invite women to have regular mammograms, which are special X‑ray images of the breast used to look for early signs of cancer. These screening programs have saved many lives.
Research shows that regular screening can reduce breast cancer deaths by about 40% to 50% among women aged between 50 and 74. Detecting cancer early gives doctors a better chance of treating it successfully.
Even though screening programs are effective, they usually follow a simple rule: most women are screened in the same way and at the same time intervals. In other words, screening often uses a “one-size-fits-all” approach.
However, doctors know that not all women have the same risk of developing breast cancer. Some women have a much higher risk than others, while some women have a very low risk.
Researchers have been trying for years to develop better ways to predict a woman’s personal risk of breast cancer. Traditional risk prediction methods usually look at factors such as family history, genetic mutations, breast density, or answers to medical questionnaires.
While these methods can provide useful information, they have not greatly changed how screening is done in everyday medical practice. Many of these tools are difficult to use widely or do not predict risk accurately enough.
A new study suggests that artificial intelligence, also known as AI, may offer a better solution. Scientists have developed a new AI-based tool that can examine mammogram images and estimate a woman’s risk of developing breast cancer over the next four years. The findings were published in the scientific journal The Lancet Digital Health.
The new system is called the BRAIx risk score. It was originally based on an AI algorithm designed to help detect breast cancer in screening scans. Researchers realized that the same technology could also be used to study subtle patterns in breast images that may indicate future cancer risk.
The advantage of using AI is that it can analyze extremely detailed information in medical images that human eyes may not notice. AI systems can examine thousands of tiny patterns in the tissue shown on mammograms and detect signals linked to future disease.
To develop the BRAIx risk score, researchers trained the AI model using mammogram images from nearly 400,000 women. The computer system studied the images and learned patterns associated with women who later developed breast cancer.
After the model was trained, the scientists tested how well it worked using new data from almost 96,000 women in Australia. To ensure the results were reliable, they also confirmed the findings in a separate group of more than 4,500 women in Sweden.
The results were striking. The AI-based risk score predicted breast cancer risk more accurately than several traditional factors doctors often use. These factors included breast density, country of birth, and even family history of breast cancer.
One of the most important findings was how strongly the tool identified women at the highest risk. Among the top 2% of women who received the highest BRAIx risk scores, almost one in ten developed breast cancer within four years. In fact, 9.7% of these women were diagnosed with cancer during that time period.
This level of risk is extremely high. According to the researchers, it is even higher than the average risk seen in women who carry inherited mutations in the BRCA1 or BRCA2 genes. These gene mutations are widely known for increasing breast cancer risk.
What makes the BRAIx system especially interesting is that it works using information already available in mammogram images. This means no additional medical tests, blood samples, or genetic analysis are required. The AI system simply analyzes the images that are already collected during routine screening.
Researchers believe this approach could make breast cancer screening more personalized. Instead of screening every woman in exactly the same way, doctors could adjust screening based on a woman’s individual risk level.
For example, women identified as having very high risk might benefit from more frequent screenings or additional imaging tests such as MRI scans. On the other hand, women with very low risk might not need screening as often.
This approach could have several benefits. It could help doctors detect cancers earlier in women who are most likely to develop them. It could also reduce unnecessary anxiety and false alarms for women who are at very low risk.
False alarms in breast cancer screening can happen when a mammogram shows something suspicious that later turns out not to be cancer. These situations can lead to extra testing and stress for patients. Better risk prediction may help reduce these unnecessary procedures.
However, the researchers caution that more studies are needed before the BRAIx risk score can be used widely in medical practice. Large clinical trials will be required to confirm that the tool improves screening outcomes and works well across different populations.
The study is still an important step forward. It shows how artificial intelligence may help doctors move toward more personalized healthcare, where treatment and prevention strategies are tailored to each individual patient.
If you care about breast cancer, please read studies about a major cause of deadly breast cancer, and this daily vitamin is critical to cancer prevention.
For more information about cancer, please see recent studies that new cancer treatment could reawaken the immune system, and results showing vitamin D can cut cancer death risk.
The research findings were published in The Lancet Digital Health.
Copyright © 2026 Knowridge Science Report. All rights reserved.
