News release

From: The Lancet

The Lancet Digital Health: AI-based tool can estimate risk of women developing breast cancer within next four years, study suggests

An artificial intelligence (AI) algorithm used to detect breast cancer in screening scans has been adapted into a risk score that estimates a woman’s risk of developing breast cancer over the next four years, according to a paper published in The Lancet Digital Health journal. The AI-based tool, called the BRAIx risk score, identified women at high risk of developing breast cancer, with nearly one in ten of those scored in the top 2% by the tool diagnosed within four years despite being given the all-clear.

While population breast cancer screening has been very successful, cutting breast cancer deaths by around 40-50% in women aged 50 to 74, it still largely takes a one-size-fits-all approach, with most women screened in the same way regardless of their personal risk of developing cancer. Traditional screening tools that try to estimate breast cancer risk using genetics, breast density or questionnaires have had limited impact in everyday clinical practice. New AI-based screening tools offer a promising way to personalise screening by using information already contained in breast scan images to better identify who is at higher or lower risk.

In this study an AI-based tool was developed using mammograms from nearly 400,000 women and then tested on data from almost 96,000 women from Australia, with the results then confirmed in an independent Swedish population of over 4500 women. The study found that the BRAIx risk score estimated breast cancer risk more accurately than the factors doctors traditionally rely on, such as breast density, country of birth, and even family history. For the top 2% of women with the highest BRAIx risk score, the probability of a cancer diagnosis within 4 years was 9.7%. This is a level of risk higher than that seen in women who carry inherited BRCA1 or BRCA2 gene mutations.

The authors say the results show how AI-based risk scores could make breast screening more personalised, helping to identify women at high risk of developing breast cancer who may benefit from closer monitoring and supplemental testing, while also identifying those at very low risk who may require less frequent screening. They say this approach could improve early cancer detection, reduce false alarms, and potentially save lives without increasing costs, although more studies are needed before it is considered for use in routine care.