Normal view

Received — 14 March 2026 ⏭ Nature Cancer

Nature Cancer
Impact of using artificial intelligence as a second reader in breast screening including arbitration Lucy M. Warren · Jenny Venton · Kenneth C. Young · Mark Halling-Brown · Christopher J. Kelly · Marc Wilson · Megumi Morigami · Lisanne Khoo · Deborah Cunningham · Richard Sidebottom · Mamatha Reddy · Hema Purushothaman · Delara Khodabakhshi · Lesley Honeyfield · Amandeep Hujan · Tsvetina Stoycheva · Andy Joiner · Reena Chopra · Aminata Sy · Dominic Ward · Lin Yang · Rory Sayres · Daniel Golden · Namrata Malhotra · Rachita Mallya · Lihong Xi · Della Ogunleye · Charlotte Purdy · Alistair Mackenzie · Susan Thomas · Shravya Shetty · Fiona J. Gilbert · Ara Darzi · Hutan Ashrafian
Nature Cancer, Published online: 10 March 2026; doi:10.1038/s43018-026-01128-zWarren et al. used data from a retrospective cohort of 50,000 women attending breast screening. Arbitration between human and AI decisions was performed in a reader study following normal arbitration workflow. After arbitration, replacing the second human reader with AI in a double-read breast screening workflow was noninferior to two human readers.
10 March 2026 at 08:00

Impact of using artificial intelligence as a second reader in breast screening including arbitration

By: Lucy M. Warren · Jenny Venton · Kenneth C. Young · Mark Halling-Brown · Christopher J. Kelly · Marc Wilson · Megumi Morigami · Lisanne Khoo · Deborah Cunningham · Richard Sidebottom · Mamatha Reddy · Hema Purushothaman · Delara Khodabakhshi · Lesley Honeyfield · Amandeep Hujan · Tsvetina Stoycheva · Andy Joiner · Reena Chopra · Aminata Sy · Dominic Ward · Lin Yang · Rory Sayres · Daniel Golden · Namrata Malhotra · Rachita Mallya · Lihong Xi · Della Ogunleye · Charlotte Purdy · Alistair Mackenzie · Susan Thomas · Shravya Shetty · Fiona J. Gilbert · Ara Darzi · Hutan Ashrafian

10 March 2026 at 08:00

Nature Cancer, Published online: 10 March 2026; doi:10.1038/s43018-026-01128-z

Warren et al. used data from a retrospective cohort of 50,000 women attending breast screening. Arbitration between human and AI decisions was performed in a reader study following normal arbitration workflow. After arbitration, replacing the second human reader with AI in a double-read breast screening workflow was noninferior to two human readers.