Eomic evaluation of artificial intelligence for cancer detection in the UK breast screening programme

Background

Artificial intelligence (AI) offers a potential solution to radiologist shortages in breast cancer screening while maintaining diagnostic accuracy. Retrospective studies suggest AI performs comparably to human readers in detecting cancers, but no economic evaluations have yet used prospective trial data.

Methods

We developed a discrete-event simulation model to estimate the cost-effectiveness of integrating AI into the NHS screening pathway using evidence from a large prospective trial. Outcomes included quality-adjusted life years (QALYs), net monetary benefit, cancer stage at detection, life years after diagnosis, cancer deaths, and healthcare costs across the screening-eligible population.

Results

AI based screening strategies increase QALYs, detect more cancers, reduce cancer deaths, and increase life years compared with the current programme. Replacing one human reader with AI generates an additional annual net monetary benefit of £7.1 million for the screened population, of which £6.3 million is cost savings to the NHS.

Conclusion

Replacing one human reader with AI is likely to be cost-effective, improve health outcomes and reduce overall costs. These results come at a crucial time as the NHS considers AI adoption to boost early detection and ease workforce pressures by reducing waiting times.