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

• Published in: Nature communications Vol. 15; no. 1; pp. 7525 - 12
• Main Authors: Frazer, Helen M. L., Peña-Solorzano, Carlos A., Kwok, Chun Fung, Elliott, Michael S., Chen, Yuanhong, Wang, Chong, Lippey, Jocelyn F., Hopper, John L., Brotchie, Peter, Carneiro, Gustavo, McCarthy, Davis J.
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 30.08.2024; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/1305; 692/308/575; 692/4028/67/1347; 692/700/1421/1770; 692/700/478/2772; Aged; Artificial Intelligence; Automation; Bias; Breast cancer; Breast Neoplasms - diagnosis; Breast Neoplasms - diagnostic imaging; Collaboration; Cooperation; Datasets; Early Detection of Cancer - methods; Female; Human performance; Humanities and Social Sciences; Humans; Mammography; Mammography - methods; Mass Screening - methods; Middle Aged; multidisciplinary; Performance degradation; Retrospective Studies; Science; Science (multidisciplinary); Sensitivity and Specificity; Victoria - epidemiology; Victoria
• ISSN: 2041-1723; 2041-1723
• DOI: 10.1038/s41467-024-51725-8

Artificial 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. Successful human-AI collaboration could greatly contribute to breast cancer mammographic screening. Here, the authors use a large-scale retrospective mammography dataset to simulate and compare five plausible AI-integrated screening pathways, finding optimal ways in which human-AI collaboration could be implemented in real-world settings.