03/10/26

Diagnostic accuracy, fairness and clinical implementation of AI for breast cancer screening: results of multicenter retrospective and prospective technical feasibility studies.

Kelly, Christopher J; Wilson, Marc; Warren, Lucy M; Sidebottom, Richard; Halling-Brown, Mark; Yang, Lin; Morigami, Megumi; Venton, Jenny; Chopra, Reena; Chang, Jane; Dixon, Jonathan; Gilbert, Fiona J; Golden, Daniel I; Gruzewska, Elzbieta; Honeyfield, Lesley; Hujan, Amandeep; Khodabakhshi, Delara; Lewis, Emma; Malhotra, Namrata; Mallya, Rachita; Ogunleye, Della; Purdy, Charlotte; Sayres, Rory; Sieniek, Marcin; Stoycheva, Tsvetina; Sy, Aminata; Thomas, Susan; Ward, Dominic; Xi, Lihong; Xu, Shawn; Shetty, Shravya; Darzi, Ara; Young, Kenneth; Purushothaman, Hema; Khoo, Lisanne; Reddy, Mamatha; Ashrafian, Hutan; Cunningham, Deborah. Nat Cancer

Summary

AI can enhance breast cancer screening by improving quality and consistency while helping address radiologist shortages. In this British study across five NHS sites, AI matched or outperformed specialist radiologists. The Google-developed AI second-reader system resulted in earlier diagnosis and reduced diagnostic errors.

Kelly CJ, Wilson M, Warren LM, et al. Diagnostic accuracy, fairness and clinical implementation of AI for breast cancer screening: results of multicenter retrospective and prospective technical feasibility studies. Nat Cancer. 2026;7(3):494-506.