Abstract
Objective: The aim of this scoping review was to evaluate whether artificial intelligence integrated into breast cancer screening work strategies could help resolve some diagnostic issues that still remain. Methods: PubMed, Web of Science, and Scopus were consulted. The literature research was updated to 28 May 2024. The PRISMA method of selecting articles was used. The articles were classified according to the type of publication (meta-analysis, trial, prospective, and retrospective studies); moreover, retrospective studies were based on citizen recruitment (organized screening vs. spontaneous screening and a combination of both). Results: Meta-analyses showed that AI had an effective reduction in the radiologists' reading time of radiological images, with a variation from 17 to 91%. Furthermore, they highlighted how the use of artificial intelligence software improved the diagnostic accuracy. Systematic review speculated that AI could reduce false negatives and positives and detect subtle abnormalities missed by human observers. DR with AI results from organized screening showed a higher recall rate, specificity, and PPV. Data from opportunistic screening found that AI could reduce interval cancer with a corresponding reduction in serious outcome. Nevertheless, the analysis of this review suggests that the study of breast density and interval cancer still requires numerous applications. Conclusions: Artificial intelligence appears to be a promising technology for health, with consequences that can have a major impact on healthcare systems. Where screening is opportunistic and involves only one human reader, the use of AI can increase diagnostic performance enough to equal that of double human reading.