Overcoming Inequity in Cancer Screening: Can Modern Technologies Close the Gap?

Cancer screening programmes have substantially reduced cancer mortality in high-income settings, yet their benefits remain unequally distributed. Current protocols are largely based on trials conducted in predominantly white, middle-income populations, leaving significant gaps for minority, low-income, and high-risk groups. Four emerging technologies-polygenic risk scores (PRS), artificial intelligence (AI)-assisted imaging, multi-cancer early detection (MCED) tests, and life-course risk models-offer the possibility of moving beyond these limitations toward more individualised, risk-based screening. However, each technology also carries the risk of reproducing or amplifying existing inequities if the conditions under which it is developed and implemented are not carefully considered. PRS models are constrained by ancestral bias in genomic datasets; AI systems have been trained predominantly on data from high-income, low-diversity populations; MCED tests remain costly and largely inaccessible outside private healthcare; and life-course models depend on integrated longitudinal data infrastructures unavailable in most low- and middle-income settings. Evidence from the NHS-Galleri trial illustrates both the promise and complexity of translating novel screening technology into population-level benefit. This review argues that achieving equitable impact will require three interconnected changes: greater diversity in training data, earlier integration of new technologies into publicly funded health systems, and parallel investment in diagnostic and follow-up capacity. Without deliberate action across these dimensions, advances in cancer screening risk benefiting those already well served while leaving the most vulnerable populations further behind.