Tang Jennifer Sn, Frazer Helen Ml, Kunicki Katrina, Basnayake Prabhathi, Omori Maho, Lippey Jocelyn
Division of Thoracic and Cardiovascular Imaging, Massachusetts General Hospital, Boston, Massachusetts, United States.
Harvard Medical School, Harvard University, Boston, Massachusetts, United States.
Prev Med Rep. 2024 Oct 28;48:102917. doi: 10.1016/j.pmedr.2024.102917. eCollection 2024 Dec.
The evolving role of Artificial Intelligence (AI) in medicine, particularly in radiology and population-based breast cancer screening programs, offers potential accuracy gains and efficiency improvements. However, successful implementation requires understanding of healthcare workers' views on AI, which this study aims to explore within the Australian BreastScreen program.
An online survey was distributed to clinical staff involved in breast imaging, collecting responses from November 2022 to April 2023. The survey encompassed demographic information, opinions, and experiences with AI in medical imaging, with questions covering various scenarios of AI integration in BreastScreen.
Out of an estimated 350 professionals contacted, 95 responded, with 84.2 % (80/95) being radiologists. Less than half of respondents (44.9 %, 40/89) had worked with artificial intelligence for image classification previously. The majority of radiologists 74.2 % (46/62) thought that the use of AI in reading mammograms for BreastScreen would improve workflow. However, radiologists thought they would behave with increasing caution with scenarios where AI was more autonomous, with the majority of radiologists (63.3 %, 38/60) uncomfortable with holding accountability when the AI was used to triage and remove cases from the workflow. Notably, 60 % of radiologists (36/60) expressed concerns about accountability.
The findings suggest an optimistic attitude towards AI among Australian healthcare workers, although when given hypothetical scenarios for the way AI could be integrated into BreastScreen, there was increasing caution with scenarios where AI was more autonomous. This study highlights understanding and concerns of healthcare professionals working in population screening which are important to address when implementing AI into the healthcare system.
人工智能（AI）在医学领域，尤其是放射学和基于人群的乳腺癌筛查项目中不断演变的作用，有望提高准确性和效率。然而，要成功实施该技术，需要了解医护人员对人工智能的看法，本研究旨在澳大利亚乳腺筛查项目中对此进行探索。
向参与乳腺成像的临床工作人员进行了一项在线调查，收集了2022年11月至2023年4月的回复。该调查涵盖了人口统计学信息、对医学成像中人工智能的看法和经验，问题涉及人工智能融入乳腺筛查的各种场景。
在估计联系的350名专业人员中，95人做出了回应，其中84.2%（80/95）是放射科医生。不到一半的受访者（44.9%，40/89）此前曾使用人工智能进行图像分类。大多数放射科医生74.2%（46/62）认为在乳腺筛查中使用人工智能阅读乳房X光片会改善工作流程。然而，放射科医生认为，在人工智能更自主的情况下，他们会越来越谨慎，大多数放射科医生（63.3%，38/60）在使用人工智能进行分流并从工作流程中剔除病例时，对承担责任感到不安。值得注意的是，60%的放射科医生（36/60）表达了对责任的担忧。
研究结果表明，澳大利亚医护人员对人工智能持乐观态度，尽管在给出人工智能融入乳腺筛查的假设场景时，对于人工智能更自主的场景越来越谨慎。本研究强调了在人群筛查中工作的医护人员的理解和担忧，这在将人工智能应用于医疗系统时很重要。
