公众号 / 文章技术与安全

医疗卫生领域中自动化图像分析与人工智能分析技术的治理

Governance of automated image analysis and artificial intelligence analytics in healthcare.
PubMed 文献 · Clin Radiol · 2019-03-19

本文讨论生物医学中人工智能治理的性质及其局限性,指出人工智能应用可能扰乱医疗情境完整性与关系动态并引发伦理法律问题。作者认为放射科医生应在推动医学进入数字时代中发挥更积极作用,承担探究人工智能临床与社会价值、弥补技术知识不足、识别并消除偏倚、应对「黑箱」障碍以及促成信息使用与安全新社会契约等专业责任,并强调伦理、法律与良好实践需更紧密结合以确保人工智能治理实现其规范目标。

要点

  • 人工智能应用可能扰乱医疗情境完整性与关系动态,引发伦理和法律问题。
  • 维持信任与可信度是治理的关键目标,需促进利益相关方协作。
  • 放射科医生应更积极参与人工智能治理并承担相应专业责任。

核心结论

  • 人工智能治理需更紧密整合伦理、法律与良好实践,才能实现其规范目标。
  • 放射科医生应承担更积极角色,包括探究人工智能临床与社会价值、弥补技术知识不足、支持识别与消除偏倚、应对「黑箱」障碍及促成信息使用与安全的新社会契约。

研究设计与样本

  • 本文为讨论生物医学中人工智能治理性质及其局限性的文章,未报告系统检索范围或纳入文献。

临床应用与阅片要点

  • 作者认为放射科医生应更积极参与推动医学进入数字时代,并承担探究人工智能临床与社会价值等专业责任。
  • 作者提出需促成关于信息使用与安全的新社会契约,并更紧密整合伦理、法律与良好实践。

局限性

  • 原文讨论了人工智能治理的局限性,但未报告具体研究设计层面的局限。

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 hype over artificial intelligence (AI) has spawned claims that clinicians (particularly radiologists) will become redundant. It is still moot as to whether AI will replace radiologists in day-to-day clinical practice, but more AI applications are expected to be incorporated into the workflows in the foreseeable future. These applications could produce significant ethical and legal issues in healthcare if they cause abrupt disruptions to its contextual integrity and relational dynamics. Sustaining trust and trustworthiness is a key goal of governance, which is necessary to promote collaboration among all stakeholders and to ensure the responsible development and implementation of AI in radiology and other areas of clinical work. In this paper, the nature of AI governance in biomedicine is discussed along with its limitations. It is argued that radiologists must assume a more active role in propelling medicine into the digital age. In this respect, professional responsibilities include inquiring into the clinical and social value of AI, alleviating deficiencies in technical knowledge in order to facilitate ethical evaluation, supporting the recognition, and removal of biases, engaging the "black box" obstacle, and brokering a new social contract on informational use and security. In essence, a much closer integration of ethics, laws, and good practices is needed to ensure that AI governance achieves its normative goals.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Ho CWL, Soon D, Caals K, et al. Governance of automated image analysis and artificial intelligence analytics in healthcare. Clin Radiol. 2019. PMID: 30898383. doi:10.1016/j.crad.2019.02.005

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。