文献速递儿科影像技术与安全

人工智能在儿科放射学中的应用:医疗专业人员意见的国际调查

Artificial intelligence in paediatric radiology: international survey of health care professionals' opinions.
PubMed 文献 · Pediatr Radiol · 2021-10-12

该研究通过2020年2月至5月的网络问卷调查了240名儿科影像相关医疗专业人员,发现多数受访者认为AI可辅助提示影像异常但希望由人工复核,不担心工作被替代,并期待AI在诊断准确性、工作流程效率和患者安全方面的发展。

要点

  • 多数受访者认为AI可提示影像异常,但83.3%要求人工复核结果。
  • 85.4%的受访者不认为AI会取代儿科放射科医生的工作。
  • AI工具开发应优先关注诊断准确性、工作流程效率和患者安全。

诊断标准与关键数值

  • 61.7%(95%CI 55.2-67.9%)的受访者同意AI可能提示放射科医生影像异常。
  • 83.3%(95%CI 78.0-87.8%)的受访者倾向于结果由人工复核。
  • 85.4%(95%CI 80.3-89.6%)的受访者不认为儿科放射学工作会被AI取代。
  • 32.1%(95%CI 26.2-38.4%)的受访者认为AI工具应关注提高诊断准确性,25.0%(95%CI 19.7-30.9%)关注工作流程效率,22.5%(95%CI 17.4-28.3%)关注患者安全。
  • 82.7%(95%CI 72.7-90.2%)的ESPR成员欢迎成立专门的儿科放射学AI工作组。

临床应用与阅片要点

  • 在临床应用中,AI提示的影像异常需由放射科医生复核确认。
  • AI工具开发应优先关注诊断准确性、工作流程效率和患者安全。

局限性

  • 研究为基于问卷的调查,可能存在回复偏倚。
  • 调查时间为2020年,结果可能随AI技术发展而变化。

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

BACKGROUND: The nature of paediatric radiology work poses several challenges for developing and implementing artificial intelligence (AI) tools, but opinions of those working in the field are currently unknown.

OBJECTIVE: To evaluate the attitudes and perceptions toward AI amongst health care professionals working within children's imaging services.

MATERIALS AND METHODS: A web-based questionnaire was distributed to the membership of several paediatric and general radiological societies over a 4-month period (1 Feb - 31 May 2020). Survey questions covered attitudes toward AI in general, future impacts and suggested areas for development specifically within paediatric imaging.

RESULTS: Two hundred and forty responses were collected with the majority being from radiologists (159/240, 66.3%; 95% confidence interval [CI] 59.8-72.2%) or allied health care professionals (72/240, 31.3%; 95% CI 25.4-37.5%). Respondents agreed that AI could potentially alert radiologists to imaging abnormalities (148/240, 61.7%; 95% CI 55.2-67.9%) but preferred that results were checked by a human (200/240, 83.3%; 95% CI 78.0-87.8%). The majority did not believe jobs in paediatric radiology would be replaced by AI (205/240, 85.4%; 95% CI 80.3-89.6%) and that the development of AI tools should focus on improved diagnostic accuracy (77/240, 32.1%; 95% CI 26.2-38.4%), workflow efficiencies (60/240, 25.0%; 95% CI 19.7-30.9%) and patient safety (54/240, 22.5%; 95% CI 17.4-28.3%). The majority of European Society of Paediatric Radiology (ESPR) members (67/81, 82.7%; 95% CI 72.7-90.2%) welcomed the idea of a dedicated paediatric radiology AI task force with emphasis on educational events and anonymised dataset curation.

CONCLUSION: Imaging health care professionals working with children had a positive outlook regarding the use of AI in paediatric radiology, and did not feel their jobs were threatened. Future AI tools would be most beneficial for easily automated tasks and most practitioners welcomed the opportunity for further AI educational activities.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Shelmerdine SC, Rosendahl K, Arthurs OJ, et al. Artificial intelligence in paediatric radiology: international survey of health care professionals' opinions. Pediatr Radiol. 2021. PMID: 34642789. doi:10.1007/s00247-021-05195-5

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。