Pearce Alison, Carter Stacy, Frazer Helen Ml, Houssami Nehmat, Macheras-Magias Mary, Webb Genevieve, Marinovich M Luke
The Daffodil Centre, The University of Sydney, A Joint Venture With Cancer Council New South Wales, Sydney, New South Wales, Australia.
Sydney School of Public Health, The University of Sydney, Sydney, New South Wales, Australia.
Cancer. 2025 May 1;131(9):e35859. doi: 10.1002/cncr.35859.
Artificial intelligence (AI) could improve accuracy and efficiency of breast cancer screening. However, many women distrust AI in health care, potentially jeopardizing breast cancer screening participation rates. The aim was to quantify community preferences for models of AI implementation within breast cancer screening.
An online discrete choice experiment survey of people eligible for breast cancer screening aged 40 to 74 years in Australia. Respondents answered 10 questions where they chose between two screening options created by an experimental design. Each screening option described the role of AI (supplementing current practice, replacing one radiologist, replacing both radiologists, or triaging), and the AI accuracy, ownership, representativeness, privacy, and waiting time. Analysis included conditional and latent class models, willingness-to-pay, and predicted screening uptake.
The 802 participants preferred screening where AI was more accurate, Australian owned, more representative and had shorter waiting time for results (all p < .001). There were strong preferences (p < .001) against AI alone or as triage. Three patterns of preferences emerged: positive about AI if accuracy improves (40% of sample), strongly against AI (42%), and concerned about AI (18%). Participants were willing to accept AI replacing one human reader if their results were available 10 days faster than current practice but would need results 21 days faster for AI as triage. Implementing AI inconsistent with community preferences could reduce participation by up to 22%.
人工智能（AI）可提高乳腺癌筛查的准确性和效率。然而，许多女性不信任医疗保健中的人工智能，这可能会危及乳腺癌筛查的参与率。目的是量化社区对乳腺癌筛查中人工智能实施模式的偏好。
对澳大利亚40至74岁符合乳腺癌筛查条件的人群进行在线离散选择实验调查。受访者回答了10个问题，他们在由实验设计创建的两种筛查选项之间进行选择。每个筛查选项描述了人工智能的作用（补充当前做法、取代一名放射科医生、取代两名放射科医生或进行分流），以及人工智能的准确性、所有权、代表性、隐私和等待时间。分析包括条件模型和潜在类别模型、支付意愿和预测的筛查接受率。
802名参与者更喜欢人工智能更准确、为澳大利亚所有、更具代表性且结果等待时间更短的筛查方式（所有p <.001）。对单独使用人工智能或作为分流方式有强烈的偏好（p <.001）。出现了三种偏好模式：如果准确性提高则对人工智能持积极态度（占样本的40%）、强烈反对人工智能（42%）以及对人工智能表示担忧（18%）。如果人工智能给出结果的时间比当前做法快10天，参与者愿意接受人工智能取代一名人工阅片者，但如果人工智能作为分流方式，则需要结果快21天。实施与社区偏好不一致的人工智能可能会使参与率降低多达22%。
Zotero 插件