Artificial intelligence is redefining the front line of breast cancer detection, offering new hope in identifying fast-growing and hard-to-treat tumours at an earlier stage, according to a landmark screening trial conducted in Sweden.
The findings, published in The Lancet, are based on data from nearly 100,000 women aged 40 to 80 who participated in Sweden’s national breast screening programme between April 2021 and December 2022.
Participants were randomly assigned either to conventional screening involving two radiologists or to an AI-assisted approach, in which artificial intelligence flagged suspicious areas on mammograms to support clinicians in making final diagnostic decisions.
Initial results showed a 44% reduction in radiologists’ workload, a development researchers say could significantly ease pressure on healthcare systems facing workforce shortages. Breast cancer remains one of the most common cancers among women, with approximately one in 20 expected to be diagnosed during their lifetime.
AI-assisted mammography is now being introduced in parts of Sweden and Denmark, underlining that the technology is designed to support rather than replace human expertise.
Dr Olga Oikonomidou, principal investigator and breast cancer research lead at the University of Edinburgh’s Cancer Centre, said the trial focused on improving radiologists’ efficiency, not removing them from the diagnostic process.
She further emphasised that as artificial intelligence becomes more widely embedded in healthcare, such systems must be subjected to the same rigorous testing and evaluation as any other medical intervention.
