[论文解读] FUTURE-AI: International consensus guideline for trustworthy and deployable artificial intelligence in healthcare

Karim Lekadir, Aasa Feragen+118 more|arXiv (Cornell University)|Aug 11, 2023

Artificial Intelligence in Healthcare and Education被引用 38

一句话总结

FUTURE-AI 提出一个国际共识框架，具有六条指引原则和 28 条建议，覆盖整个生命周期以开发、部署并监控可信的医疗 AI。

ABSTRACT

Despite major advances in artificial intelligence (AI) for medicine and healthcare, the deployment and adoption of AI technologies remain limited in real-world clinical practice. In recent years, concerns have been raised about the technical, clinical, ethical and legal risks associated with medical AI. To increase real world adoption, it is essential that medical AI tools are trusted and accepted by patients, clinicians, health organisations and authorities. This work describes the FUTURE-AI guideline as the first international consensus framework for guiding the development and deployment of trustworthy AI tools in healthcare. The FUTURE-AI consortium was founded in 2021 and currently comprises 118 inter-disciplinary experts from 51 countries representing all continents, including AI scientists, clinicians, ethicists, and social scientists. Over a two-year period, the consortium defined guiding principles and best practices for trustworthy AI through an iterative process comprising an in-depth literature review, a modified Delphi survey, and online consensus meetings. The FUTURE-AI framework was established based on 6 guiding principles for trustworthy AI in healthcare, i.e. Fairness, Universality, Traceability, Usability, Robustness and Explainability. Through consensus, a set of 28 best practices were defined, addressing technical, clinical, legal and socio-ethical dimensions. The recommendations cover the entire lifecycle of medical AI, from design, development and validation to regulation, deployment, and monitoring. FUTURE-AI is a risk-informed, assumption-free guideline which provides a structured approach for constructing medical AI tools that will be trusted, deployed and adopted in real-world practice. Researchers are encouraged to take the recommendations into account in proof-of-concept stages to facilitate future translation towards clinical practice of medical AI.

研究动机与目标

• 通过建立正式的国际共识来提升医疗保健领域可信 AI 的现实世界采用程度。
• 定义覆盖整个 AI 生命周期的综合框架——从设计与开发到部署与监控。
• 确立六条指引原则（公平性、普遍性、可追溯性、可用性、鲁棒性、可解释性）及可操作的最佳实践。
• 提供一个以风险为导向、无假设的指南，以促进医疗 AI 向临床实践的转化。

提出的方法

• 组建了一个由 118 名成员组成的跨学科、国际联盟，涵盖 51 个国家。
• 在 24 个月内采用多阶段德尔菲法流程及在线共识会议。
• 进行了深入的文献综述，以确定与医学领域可信 AI 相关的维度。
• 制定了受 FAIR 数据原则启发的六条指引原则。
• 生成并迭代修订了一组建议（54 → 22 → 30 → 最终 28）。
• 应用机器学习技术就绪度水平（ ML-TRL）视角，以区分概念验证阶段与可投入部署的 AI 的建议。

实验结果

研究问题

• RQ1 在医疗保健中，可信 AI 需要哪些指引原则？
• RQ2 哪些具体最佳实践能够在 AI 生命周期中确保公平性、普遍性、可追溯性、易用性、鲁棒性和可解释性？
• RQ3 在早期研究与临床部署之间，建议应如何区分（ML-TRL 区分）？
• RQ4 如何在医学的不同设定和领域中实现并落地国际共识？

主要发现

• 确立了用于可信医疗 AI 的六条指引原则：公平性、普遍性、可追溯性、易用性、鲁棒性、可解释性。
• 界定了覆盖技术、临床、法律和社会伦理维度的 28 条具体建议。
• 证明这些建议适用于整个 AI 生命周期（设计、开发、验证、监管、部署、监测）。
• 引入基于 ML-TRL 的区分，以定制概念验证工具与可部署工具的建议。
• 通过迭代调查、专家反馈轮次以及四次在线共识会议，达成广泛的国际共识。