Comparison of AI-integrated pathways with human-AI interaction in population mammographic screening for breast cancer

Simple item page
dc.contributor.authorFrazer, H.M.L.
dc.contributor.authorPeña-Solorzano, C.A.
dc.contributor.authorKwok, C.F.
dc.contributor.authorElliott, M.S.
dc.contributor.authorChen, Y.
dc.contributor.authorWang, C.
dc.contributor.authorLippey, J.F.
dc.contributor.authorHopper, J.L.
dc.contributor.authorBrotchie, P.
dc.contributor.authorCarneiro, G.
dc.contributor.authorMcCarthy, D.J.
dc.date.issued2024
dc.description.abstractArtificial intelligence (AI) readers of mammograms compare favourably to individual radiologists in detecting breast cancer. However, AI readers cannot perform at the level of multi-reader systems used by screening programs in countries such as Australia, Sweden, and the UK. Therefore, implementation demands human-AI collaboration. Here, we use a large, high-quality retrospective mammography dataset from Victoria, Australia to conduct detailed simulations of five potential AI-integrated screening pathways, and examine human-AI interaction effects to explore automation bias. Operating an AI reader as a second reader or as a high confidence filter improves current screening outcomes by 1.9-2.5% in sensitivity and up to 0.6% in specificity, achieving 4.6-10.9% reduction in assessments and 48-80.7% reduction in human reads. Automation bias degrades performance in multi-reader settings but improves it for single-readers. This study provides insight into feasible approaches for AI-integrated screening pathways and prospective studies necessary prior to clinical adoption.
dc.description.statementofresponsibilityHelen M. L. Frazer, Carlos A. Peña-Solorzano, Chun Fung Kwok, Michael S. Elliott, Yuanhong Chen, Chong Wang, The BRAIx Team, Jocelyn F. Lippey, John L. Hopper, Peter Brotchie, Gustavo Carneiro, Davis J. McCarthy
dc.identifier.citationNature Communications, 2024; 15(1):7525-1-7525-12
dc.identifier.doi10.1038/s41467-024-51725-8
dc.identifier.issn2041-1723
dc.identifier.issn2041-1723
dc.identifier.orcidCarneiro, G. [0000-0002-5571-6220]
dc.identifier.urihttps://hdl.handle.net/2440/143505
dc.language.isoen
dc.publisherNature Portfolio
dc.relation.granthttp://purl.org/au-research/grants/nhmrc/GNT1195595
dc.relation.granthttp://purl.org/au-research/grants/nhmrc/GNT1195595
dc.source.urihttp://dx.doi.org/10.1038/s41467-024-51725-8
dc.subjectBreast cancer; Machine learning; Population screening; Radiography; Translational research
dc.subject.meshHumans
dc.subject.meshBreast Neoplasms
dc.subject.meshMammography
dc.subject.meshMass Screening
dc.subject.meshSensitivity and Specificity
dc.subject.meshRetrospective Studies
dc.subject.meshArtificial Intelligence
dc.subject.meshAged
dc.subject.meshMiddle Aged
dc.subject.meshVictoria
dc.subject.meshFemale
dc.subject.meshEarly Detection of Cancer
dc.titleComparison of AI-integrated pathways with human-AI interaction in population mammographic screening for breast cancer
dc.typeJournal article
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
hdl_143505.pdf
Size:
5.33 MB
Format:
Adobe Portable Document Format
Description:
Published version
Download

Collections

Research Outputs