International evaluation of an AI system for breast cancer screening

Scott Mayer McKinney (), Marcin Sieniek, Varun Godbole, Jonathan Godwin, Natasha Antropova, Hutan Ashrafian, Trevor Back, Mary Chesus, Greg S. Corrado, Ara Darzi, Mozziyar Etemadi, Florencia Garcia-Vicente, Fiona J. Gilbert, Mark Halling-Brown, Demis Hassabis, Sunny Jansen, Alan Karthikesalingam, Christopher J. Kelly, Dominic King, Joseph R. Ledsam, David Melnick, Hormuz Mostofi, Lily Peng, Joshua Jay Reicher, Bernardino Romera-Paredes, Richard Sidebottom, Mustafa Suleyman, Daniel Tse (), Kenneth C. Young, Jeffrey Fauw and Shravya Shetty ()
Additional contact information
Scott Mayer McKinney: Google Health
Marcin Sieniek: Google Health
Varun Godbole: Google Health
Jonathan Godwin: DeepMind
Natasha Antropova: DeepMind
Hutan Ashrafian: Imperial College London
Trevor Back: DeepMind
Mary Chesus: DeepMind
Greg S. Corrado: Google Health
Ara Darzi: Imperial College London
Mozziyar Etemadi: Northwestern Medicine
Florencia Garcia-Vicente: Northwestern Medicine
Fiona J. Gilbert: University of Cambridge
Mark Halling-Brown: Royal Surrey County Hospital
Demis Hassabis: DeepMind
Sunny Jansen: Verily Life Sciences
Alan Karthikesalingam: Google Health
Christopher J. Kelly: Google Health
Dominic King: Google Health
Joseph R. Ledsam: DeepMind
David Melnick: Northwestern Medicine
Hormuz Mostofi: Google Health
Lily Peng: Google Health
Joshua Jay Reicher: Stanford Health Care and Palo Alto Veterans Affairs
Bernardino Romera-Paredes: DeepMind
Richard Sidebottom: The Royal Marsden Hospital
Mustafa Suleyman: DeepMind
Daniel Tse: Google Health
Kenneth C. Young: Royal Surrey County Hospital
Jeffrey Fauw: DeepMind
Shravya Shetty: Google Health

Nature, 2020, vol. 577, issue 7788, 89-94

Abstract: Abstract Screening mammography aims to identify breast cancer at earlier stages of the disease, when treatment can be more successful1. Despite the existence of screening programmes worldwide, the interpretation of mammograms is affected by high rates of false positives and false negatives2. Here we present an artificial intelligence (AI) system that is capable of surpassing human experts in breast cancer prediction. To assess its performance in the clinical setting, we curated a large representative dataset from the UK and a large enriched dataset from the USA. We show an absolute reduction of 5.7% and 1.2% (USA and UK) in false positives and 9.4% and 2.7% in false negatives. We provide evidence of the ability of the system to generalize from the UK to the USA. In an independent study of six radiologists, the AI system outperformed all of the human readers: the area under the receiver operating characteristic curve (AUC-ROC) for the AI system was greater than the AUC-ROC for the average radiologist by an absolute margin of 11.5%. We ran a simulation in which the AI system participated in the double-reading process that is used in the UK, and found that the AI system maintained non-inferior performance and reduced the workload of the second reader by 88%. This robust assessment of the AI system paves the way for clinical trials to improve the accuracy and efficiency of breast cancer screening.

Date: 2020
References: Add references at CitEc
Citations: View citations in EconPapers (16)

Downloads: (external link)
https://www.nature.com/articles/s41586-019-1799-6 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:nat:nature:v:577:y:2020:i:7788:d:10.1038_s41586-019-1799-6

Ordering information: This journal article can be ordered from
https://www.nature.com/

DOI: 10.1038/s41586-019-1799-6

Access Statistics for this article

Nature is currently edited by Magdalena Skipper

More articles in Nature from Nature
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().