人工智能干预临床试验报告指南:SPIRIT-AI与CONSORT-AI
SPIRIT-AI与CONSORT-AI是首个针对AI系统临床试验的国际报告标准,由多学科国际专家组采用共识构建方法制定。该扩展指南在SPIRIT与CONSORT核心条目基础上新增AI特异性报告条目,如算法版本和输入数据获取流程,旨在确保AI干预临床试验方案与报告的完整性和透明性,提升试验设计与实施质量。
要点
- AI临床试验方案与报告应遵循SPIRIT-AI和CONSORT-AI扩展指南。
- 需额外报告算法版本、输入数据获取流程等AI特异性条目。
- 指南旨在提升AI干预临床试验的完整性与透明性。
核心结论
- SPIRIT-AI和CONSORT-AI指南提供了AI系统临床试验的首个国际标准,旨在确保涉及AI干预的临床试验方案和报告完整透明。
研究设计与样本
- 由多学科国际专家组采用共识构建方法制定,作为SPIRIT和CONSORT的扩展。
主要发现
- 现有SPIRIT和CONSORT指南未充分涵盖AI系统特有的偏倚来源。
- 需特殊报告的元素包括算法版本和输入数据获取流程。
- 扩展指南包含在核心条目之外新增的若干报告条目。
关键数值与推荐
- 每个新增条目尽可能参考了现有AI系统健康应用研究中识别的挑战。
临床怎么用
- 在AI干预临床试验的方案设计和结果报告中应用SPIRIT-AI和CONSORT-AI扩展条目,以提升报告完整性和透明度。
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)。
原文
BACKGROUND: 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. MAIN TEXT: 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. CONCLUSION: 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.
引用
- Ibrahim H, Liu X, Rivera SC, et al. Reporting guidelines for clinical trials of artificial intelligence interventions: the SPIRIT-AI and CONSORT-AI guidelines. Trials. 2021. PMID: 33407780. doi:10.1186/s13063-020-04951-6
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。