New research has discovered that the use of AI in breast cancer screening can increase detection by 10.4% – and has the potential to reduce the workload of healthcare workers by more than 30%.

Cited as the UK’s first comprehensive evaluation of AI in breast cancer screens, the study was carried out by a team of scientists, clinicians, and software developers from the University of Aberdeen, NHS Grampian, and Kheiron Medical Technologies.

The study found that not only did AI help with cancer detection by spotting more cancers, most of which were invasive and high grade, but it could also reduce the time to notify affected people from 14 days to just 3.

The authors of the study, which has been published today in the Nature Cancer journal, said that this is “hugely significant given that the earlier detection of primarily high-grade cancers enables earlier treatment.”

The Scots researchers assessed how an AI software tool — Mia, developed by Kheiron Medical Technologies — could be used to support healthcare workers in routine breast screenings of nearly 11,000 people in NHS Grampian.

To evaluate the different ways in which AI could support breast screening, and which were most successful, 17 scenarios were tested by incorporating AI into the existing breast screening workflow at various points.

The results showed that combining AI as a second reader to replace one human, and as an extra reader serving as a safeguard, resulted in the best combination for increased early cancer detection without recalls — as well as workload savings.

Professor Gerald Lip, the clinical director for breast screening in the North East of Scotland in NHS Grampian and lead for AI in clinical practice at the University of Aberdeen said: “Our results show that AI could effectively support breast screening services by increasing cancer detection and reducing doctors’ workload.

“Ultimately, for radiologists, AI augments practice. Along with picking up more cancers, in UK and European screening programs where mammograms are read by two humans, partial substitution of one of the human readers for normal examinations can deliver real workload savings and reduce burnout. The bottom line here is – without AI, doctors would not have caught these cancers as early.

“The translation of AI into clinical practice is one of the operational challenges in the coming decade. Our findings and the novel way we have conducted this prospective study will inform the conversation around using AI in healthcare.”

Recommended reading

• Half of People in Scotland Use AI for Health Diagnosis
• Could This Smart Pillow Stop Nighttime Doomscrolling?
• Can You Trust Digital Tools With Your Mental Health?

While further research is required to fully quantify the benefits — as well as potential harms — the study provides a foundation for the next steps in this field.

It also directly supports the upcoming EDITH (“Early Detection using Information Technology in Health”) trial, which will expand this work to evaluate the use of AI in breast screening across sites throughout the UK.

The Scottish element of the trial will be led jointly by the University of Aberdeen, NHS Grampian, and University of Glasgow.