Economic 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 de novo discrete-event simulation model to estimate the cost-effectiveness of integrating AI into the NHS screening pathway using evidence from a large prospective trial. RESULTS: The AI-only strategy generated a small incremental QALY gain of 0.00009 and reduced lifetime costs by £159.55 per woman invited, and had a 100% probability of being most cost-effective at the £20,000/QALY threshold. Replacing one human reader with AI also increased QALYs, by 0.00019, and reduced costs by £31.07. Triple reading (two humans plus AI) produced the largest QALY gain (0.00023) but increased costs by £72.79. All AI-based pathways reduced cancer deaths, shifted cancers from advanced (TNM stage 4) to earlier stages at detection, and increased the proportion of cancers detected by screening. CONCLUSION: Using AI in place of human readers is likely to be cost-effective, marginally improving health outcomes while reducing overall costs, with full replacement of both human readers being the most cost-effective screening strategy.