Scottish study shows AI increases cancer detection by more than 10 per cent

Artificial intelligence (AI) evaluation in breast cancer screening has been found to increase detection by over 10 per cent, according to the UK’s first comprehensive study into the technology.  

The evaluation, which has been published in Nature Cancer by a team of scientists, clinicians, and software developers from the University of Aberdeen, NHS Grampian, and Kherion Medical Technologies, found that the technology has the potential to reduce the workload of healthcare workers by more than 30 per cent compared to the current clinical process. 

The study found that AI is not only helping to detect more cancers, most of which are invasive and high-grade, but it can also reduce the time to notify affected women from 14 days to just three. 

Authors of the research have described this development as “hugely significant” and say it will enable earlier treatment, which has “a greater likelihood of treatment success”. 

It was also found that using AI as part of the large-scale screening programme could reduce the number of women who are unnecessarily recalled for further assessment – including unnecessary biopsies.  

The evaluation followed NHS Grampian's GEMINI (Grampian’s Evaluation of Mia in an Innovative National breast screening Initiative) project, which was facilitated by the North of Scotland NHS Innovation Hub. 

Researchers assessed how the AI software tool, developed by Kherion Medical Technologies, can be used to support healthcare workers in the routine breast screening of 10,889 women in NHS Grampian. 

Dr Clarisse de Vries, lecturer in data science at the University of Glasgow, lead author and former research fellow at the University of Aberdeen, said over two million mammogram examinations are carried out each year on women between 50 and 70 years old, and currently, for the two radiologists who read every mammogram, “some breast cancers are extremely hard to detect”.  

She said: “Currently, in the UK, to reduce the number of cancers missed, two radiologists read every mammogram. However, some breast cancers are extremely hard to detect, and it is not always clear from mammograms whether breast cancer is present. So, when there is the suspicion of cancer on a mammogram, the woman is recalled for additional investigations. 

“Despite this, approximately 20 per cent of cancers are missed using this process. 

“Furthermore, many more women are recalled for further assessments than are diagnosed with cancer. For each five women recalled, approximately one will be diagnosed with breast cancer. So, they have had unnecessary, often invasive tests – not to mention the additional worry for the patient. 

“This is why our findings are so important – not only did we find optimal ways to detect breast cancer, quicker and more accurately, we also found ways to reduce the number of women having to return for unnecessary tests.” 

Professor Gerald Lip, clinical director for breast screening in the North East of Scotland in NHS Grampian and lead for artificial intelligence in clinical practice at the University of Aberdeen, added: “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.”