Academic Unit of Ophthalmology, Institute of Inflammation and Ageing, College of Medical and Dental Sciences, University of Birmingham, Birmingham, B15 2TT, UK.
University Hospitals Birmingham NHS Foundation Trust, Birmingham, UK.
Trials. 2021 Jan 6;22(1):11. doi: 10.1186/s13063-020-04951-6.
The application of artificial intelligence (AI) in healthcare is an area of immense interest. The high profile of 'AI in health' means that there are unusually strong drivers to accelerate the introduction and implementation of innovative AI interventions, which may not be supported by the available evidence, and for which the usual systems of appraisal may not yet be sufficient.
We are beginning to see the emergence of randomised clinical trials evaluating AI interventions in real-world settings. It is imperative that these studies are conducted and reported to the highest standards to enable effective evaluation because they will potentially be a key part of the evidence that is used when deciding whether an AI intervention is sufficiently safe and effective to be approved and commissioned. Minimum reporting guidelines for clinical trial protocols and reports have been instrumental in improving the quality of clinical trials and promoting completeness and transparency of reporting for the evaluation of new health interventions. The current guidelines-SPIRIT and CONSORT-are suited to traditional health interventions but research has revealed that they do not adequately address potential sources of bias specific to AI systems. Examples of elements that require specific reporting include algorithm version and the procedure for acquiring input data. In response, the SPIRIT-AI and CONSORT-AI guidelines were developed by a multidisciplinary group of international experts using a consensus building methodological process. The extensions include a number of new items that should be reported in addition to the core items. Each item, where possible, was informed by challenges identified in existing studies of AI systems in health settings.
The SPIRIT-AI and CONSORT-AI guidelines provide the first international standards for clinical trials of AI systems. The guidelines are designed to ensure complete and transparent reporting of clinical trial protocols and reports involving AI interventions and have the potential to improve the quality of these clinical trials through improvements in their design and delivery. Their use will help to efficiently identify the safest and most effective AI interventions and commission them with confidence for the benefit of patients and the public.
人工智能（AI）在医疗保健中的应用是一个极受关注的领域。“AI 在健康领域”的高知名度意味着有异常强大的动力来加速创新 AI 干预措施的引入和实施，而这些干预措施可能没有得到现有证据的支持，并且通常的评估系统可能还不够充分。
我们开始看到在真实环境中评估 AI 干预措施的随机临床试验的出现。这些研究必须按照最高标准进行和报告，以实现有效的评估，因为它们可能是决定 AI 干预措施是否足够安全有效的关键证据之一，以获得批准和委托。临床试验方案和报告的最低报告指南在提高临床试验质量和促进新健康干预措施评估的完整性和透明度方面发挥了重要作用。当前的指南-SPIRIT 和 CONSORT-适用于传统的健康干预措施，但研究表明它们不能充分解决 AI 系统特有的潜在偏差来源。需要具体报告的示例包括算法版本和获取输入数据的程序。作为回应，SPIRIT-AI 和 CONSORT-AI 指南由一组多学科的国际专家使用共识建立方法学过程开发。扩展包括除核心项目外还应报告的一些新项目。每个项目尽可能地借鉴了在健康环境中研究 AI 系统的现有研究中确定的挑战。
SPIRIT-AI 和 CONSORT-AI 指南为 AI 系统临床试验提供了第一个国际标准。这些指南旨在确保涉及 AI 干预措施的临床试验方案和报告的完整和透明报告，并有可能通过改进其设计和实施来提高这些临床试验的质量。它们的使用将有助于有效地确定最安全和最有效的 AI 干预措施，并满怀信心地委托它们为患者和公众的利益服务。
