Semi-Automated Checking of Research Outputs

研究成果的半自动检查

• 批准号: MC_PC_23006
• 负责人: James Smith
• 金额: $ 65.61万
• 依托单位: University of the West of England
• 依托单位国家: 英国
• 项目类别: Intramural
• 财政年份: 2023
• 资助国家: 英国
• 起止时间: 2023 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=MC_PC_23006
• 关键词: Semi; Automated; Checking; Research; Outputs

Trusted Research Environments (TREs) play a vital role in enabling researchers to analyse confidential data such as health records then report findings. The Five-SafesFramework is used to ensure data confidentiality and includes Safe Outputs. Outputs are typically checked by two expert staff before release, which is a significant expense for TREoperators, and can cause a bottleneck for researchers.Meanwhile, the parallel development of TREs and understanding of disclosure-risk, hascreated a need to consolidate theory and practice to minimise inconsistent behaviourbetween TREs. Addressing both these issues, this project seeks to reduce the operating costs of TREs, and the time taken to release research results. It will:•Produce a consolidated framework with a rigorous statistical basis that providesguidance for TREs to agree consistent, standard processes to assist in QualityAssurance.•Design and implement a semi-automated system for checks on common research outputs, with increasing levels of support for other types such as AI.•Work with a range of different types of TRE in different sectors (health, social data)and organisations (academia, government, private sector) to ensure wide applicability.•Work with public and patients to explore what is needed for public trust that anyautomation is acting as “an extra pair of eyes”: supporting not supplanting TRE staff,helping them to make easy decisions more rapidly and therefore focus on more complex or nuanced cases.

可信研究环境 (TRE) 在使研究人员能够分析健康记录等机密数据并报告结果方面发挥着至关重要的作用。五安全框架用于确保数据机密性，并且安全输出通常由两名专家人员在发布前进行检查。这对于 TRE 运营商来说是一笔巨大的开支，并且可能会给研究人员造成瓶颈。同时，TRE 的并行开发和对披露风险的理解需要巩固理论和实践，以最大限度地减少 TRE 之间的不一致行为 为了解决这两个问题，该项目旨在降低 TRE 的运营成本以及发布研究结果所需的时间。 它将： • 制定一个具有严格统计基础的综合框架，为 TRE 提供指导。同意一致的标准流程以协助质量保证。•设计和实施半自动化系统，用于检查常见研究成果，并增加对人工智能等其他类型的支持水平。•与一系列不同类型的 TRE 合作不同部门（健康、社会数据）和组织（学术界、政府、私营部门），以确保广泛的适用性。与公众和患者合作，探索如何让公众相信任何自动化都可以充当“额外的眼睛” ：支持而不是取代 TRE 员工，帮助他们更快地做出简单的决策，从而专注于更复杂或微妙的案例。

项目成果

Machine learning models in trusted research environments -- understanding operational risks

可信研究环境中的机器学习模型——了解运营风险

• DOI: 10.23889/ijpds.v8i1.2165
• 发表时间: 2023
• 期刊: International Journal of Population Data Science
• 作者: Ritchie F

The inadvertently revealing statistic: A systemic gap in statistical training?

无意中揭示的统计数据：统计培训中的系统性差距？

• DOI: 10.1093/jrssig/qmae009
• 发表时间: 2024
• 期刊: Significance
• 作者: Derrick B