Ozcan B Bersu, Dogan Basak E, Xi Yin, Knippa Emily E
Department of Radiology, University of Texas Southwestern Medical Center, 5323 Harry Hines Blvd, MC 8896, Dallas, TX 75390-8896.
Department of Population and Data Sciences, University of Texas Southwestern Medical Center, Department of Population and Data Sciences, Dallas, Tex.
Radiol Imaging Cancer. 2025 May;7(3):e240290. doi: 10.1148/rycan.240290.
Purpose To assess patient perceptions of artificial intelligence (AI) use in the interpretation of screening mammograms. Materials and Methods In a prospective, institutional review board-approved study, all patients undergoing mammography screening at the authors' institution between February 2023 and August 2023 were offered a 29-question survey. Age, race and ethnicity, education, income level, and history of breast cancer and biopsy were collected. Univariable and multivariable logistic regression analyses were used to identify the independent factors associated with participants' acceptance of AI use. Results Of the 518 participants, the majority were between the ages of 40 and 69 years (377 of 518, 72.8%), at least college graduates (347 of 518, 67.0%), and non-Hispanic White (262 of 518, 50.6%). Participant-reported knowledge of AI was none or minimal in 76.5% (396 of 518). Stand-alone AI interpretation was accepted by 4.44% (23 of 518), whereas 71.0% (368 of 518) preferred AI to be used as a second reader. After an AI-reported abnormal screening, 88.9% (319 of 359) requested radiologist review versus 51.3% (184 of 359) of radiologist recall review by AI ( < .001). In cases of discrepancy, higher rate of participants would undergo diagnostic examination for radiologist recalls compared with AI recalls (94.2% [419 of 445] vs 92.6% [412 of 445]; = .20]. Higher education was associated with higher AI acceptance (odds ratio [OR] 2.05, 95% CI: 1.31, 3.20; = .002). Race was associated with higher concern for bias in Hispanic versus non-Hispanic White participants (OR 3.32, 95% CI: 1.15, 9.61; = .005) and non-Hispanic Black versus non-Hispanic White participants (OR 4.31, 95% CI: 1.50, 12.39; = .005). Conclusion AI use as a second reader of screening mammograms was accepted by participants. Participants' race and education level were significantly associated with AI acceptance. Breast, Mammography, Artificial Intelligence Published under a CC BY 4.0 license.
目的 评估患者对人工智能（AI）用于筛查乳腺钼靶影像解读的看法。材料与方法 在一项经机构审查委员会批准的前瞻性研究中，2023年2月至2023年8月期间在作者所在机构接受乳腺钼靶筛查的所有患者均被提供一份包含29个问题的调查问卷。收集了年龄、种族和族裔、教育程度、收入水平以及乳腺癌和活检病史。采用单变量和多变量逻辑回归分析来确定与参与者接受AI使用相关的独立因素。结果 在518名参与者中，大多数年龄在40至69岁之间（518名中的377名，72.8%），至少是大学毕业生（518名中的347名，67.0%），且为非西班牙裔白人（518名中的262名，50.6%）。76.5%（518名中的396名）的参与者报告对AI的了解为无或极少。4.44%（518名中的23名）接受独立的AI解读，而71.0%（518名中的368名）更倾向于将AI用作第二阅片者。在AI报告筛查异常后，88.9%（359名中的319名）要求放射科医生复查，而AI召回放射科医生复查的比例为51.3%（359名中的184名）（P <.001）。在存在差异的情况下，与AI召回相比，更多参与者会因放射科医生召回而接受诊断检查（94.2%[445名中的419名]对92.6%[445名中的412名]；P =.20）。高等教育与更高的AI接受度相关（优势比[OR]2.05，95%置信区间：1.31，3.20；P =.002）。种族方面，西班牙裔与非西班牙裔白人参与者相比（OR 3.32，95%置信区间：1.15，9.61；P =.005）以及非西班牙裔黑人与非西班牙裔白人参与者相比（OR 4.31，95%置信区间：1.50，12.39；P =.005），对偏差的担忧更高。结论 参与者接受将AI用作筛查乳腺钼靶的第二阅片者。参与者的种族和教育水平与AI接受度显著相关。乳腺、乳腺钼靶、人工智能 依据知识共享署名4.0许可协议发布。
