文献速递儿科影像技术与安全

人工智能与儿科影像数据:学习与合作的伦理策略

Artificial intelligence and pediatric imaging data: ethical strategies for learning and collaboration.
PubMed 文献 · Pediatr Radiol · 2025-12-26

本文综述了人工智能在儿科影像中应用的伦理挑战,包括监管障碍、偏见缓解和人类监督的必要性。强调需要跨学科合作、持续教育以及患者和家庭的参与,以优先保障年轻患者的长期安全与健康。

要点

  • 儿科影像AI应用需优先考虑透明度、问责制和开发者、临床医生与监管机构间的合作。
  • 儿科放射科医生需具备批判性评估AI输出及识别潜在偏见与局限的能力。
  • AI整合需患者和家庭参与,多利益相关方协调以保障年轻患者长期安全。

核心结论

  • 儿科影像中AI的整合需要所有利益相关方协调努力,优先考虑年轻患者的长期安全与健康。

研究设计与样本

  • 综述,未报告检索范围与纳入文献数量。

临床应用与阅片要点

  • 儿科放射科医生需要接受儿科放射学和AI的持续教育与培训,以批判性评估AI输出。
  • AI整合需要开发者、临床医生、监管机构以及患者和家庭的协作参与。

局限性

  • 原文未报告局限性

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

The integration of artificial intelligence (AI) in pediatric radiology requires an interdisciplinary approach that prioritizes transparency, accountability and collaboration between developers, clinicians and regulatory bodies. The development of AI models that are specifically designed to analyze pediatric imaging data has the potential to improve diagnosis and treatment outcomes, but it also requires careful consideration of the ethical implications. This review highlights the importance of the unique challenges posed by AI in pediatric imaging data, including regulatory hurdles, bias mitigation and the need for human oversight. Facing this situation, pediatric radiologists need to be equipped with the skills and knowledge to critically evaluate AI outputs and address potential biases and limitations. This requires ongoing education and training in pediatric radiology as well as AI. The integration of AI in pediatric radiology requires a collaborative approach that involves not only developers and clinicians but also patients and families. Ultimately, the integration of AI in pediatric imaging needs to be a coordinated effort from all stakeholders to prioritize the long-term safety and health of the young patients.

来源:Pediatr Radiol,查看原文。版权归原作者所有。

引用

  1. Vrettos K, Giouroukou K, Isaac A, et al. Artificial intelligence and pediatric imaging data: ethical strategies for learning and collaboration. Pediatr Radiol. 2025. PMID: 41452364. doi:10.1007/s00247-025-06497-8

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。