文献速递技术与安全

放射科医生、信息技术专家与行业代表对人工智能的态度调查

Attitudes Toward Artificial Intelligence Among Radiologists, IT Specialists, and Industry.
PubMed 文献 · Acad Radiol · 2020-05-13

2019年一次全国性人工智能、电子健康与信息技术基础设施会议上,对123名参会者进行28项问卷调查,比较放射科医生、信息技术专家与行业代表对人工智能及其对放射学工作未来影响的态度。结果显示各方对人工智能未来角色期望高但对其结果信心低,且要求合理性检查与随机对照研究验证。

要点

  • 受访者普遍认同合理性检查对理解人工智能决策重要(93%同意)且人工智能算法验证是强制性的(91%)。
  • 仅25%的受访者对人工智能结果有信心,仅17%认为医学将因人工智能更人性化。
  • 三个职业群体在四个条目上回答存在显著差异,包括横断面成像协议选择的相关性等。

核心结论

  • 目前对人工智能未来角色的高期望与对其结果的低信心之间存在差距,且该态度在三个群体中相似。
  • 对合理性检查的需求及需在随机对照研究中证明有用性,指明了未来研究所需的方向。

研究设计与样本

  • 研究类型为问卷调查,于2019年一次全国性人工智能、电子健康与信息技术基础设施会议上进行。
  • 共123名参会者完成28项探索医学中人工智能使用的条目。
  • 使用Kruskal-Wallis检验识别放射科医生、信息技术专家与行业代表之间的差异。

诊断标准与关键数值

  • 全体受访者同意率最高的条目:合理性检查对理解人工智能决策重要(93%同意)、人工智能算法验证是强制性的(91%)、医学在人工智能时代变得更高效(86%)。
  • 仅25%的受访者对人工智能结果有信心,仅17%认为医学将通过使用人工智能变得更人性化。
  • 三个职业群体在四个条目上回答存在显著差异:横断面成像中协议选择的相关性(p = 0.034)、医学会应参与验证(p = 0.028)、患者应被告知人工智能的使用(p = 0.047)、人工智能应成为医学教育的一部分(p = 0.026)。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

英文原文(摘要)· 点击展开

OBJECTIVES: We investigated the attitudes of radiologists, information technology (IT) specialists, and industry representatives on artificial intelligence (AI) and its future impact on radiological work.

MATERIALS AND METHODS: During a national meeting for AI, eHealth, and IT infrastructure in 2019, we conducted a survey to obtain participants' attitudes. A total of 123 participants completed 28 items exploring AI usage in medicine. The Kruskal-Wallis test was used to identify differences between radiologists, IT specialists, and industry representatives.

RESULTS: The strongest agreement between all respondents occurred with the following: plausibility checks are important to understand the decisions of the AI (93% agreement), validation of AI algorithms is mandatory (91%), and medicine becomes more efficient in the age of AI (86%). In contrast, only 25% of the respondents had confidence in the AI results, and only 17% believed that medicine will become more human through the use of AI. The answers were significantly different between the three professions for four items: relevance for protocol selection in cross-sectional imaging (p = 0.034), medical societies should be involved in validation (p = 0.028), patients should be informed about the use of AI (p = 0.047), and AI should be part of medical education (p = 0.026).

CONCLUSION: Currently, a discrepancy exists between high expectations for the future role of AI and low confidence in the results. This attitude was similar across all three groups. The demand for plausibility checks and the need to prove the usefulness in randomized controlled studies indicate what is needed in future research.

来源:Acad Radiol,查看原文。版权归原作者所有。

引用

  1. Jungmann F, Jorg T, Hahn F, et al. Attitudes Toward Artificial Intelligence Among Radiologists, IT Specialists, and Industry. Acad Radiol. 2020. PMID: 32414637. doi:10.1016/j.acra.2020.04.011

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。