Semi-Automated Risk Assessment of Data Provenance and Clinical Free-text in TREs

TRE 中数据来源和临床自由文本的半自动风险评估

• 批准号: MC_PC_23005
• 负责人: Arlene Casey
• 金额: $ 48.82万
• 依托单位: University of Edinburgh
• 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_23005
• 关键词: Semi; Automated; Risk; Assessment; Data

Data is transforming health and social care, enabling life-changing discoveries, advancing healthcare services, and improving lives. Yet health data providers face challenges in extracting and linking this complex data and safeguarding its safe release for research. Risk assessments are key to ensure that data releases do not pose privacy risks, such as containing identifiable patient information or that patients’ records are processed correctly. However, currently these governance processes are ad-hoc, manual, time consuming and may prohibit data release, ultimately limiting new health and social care innovation.This project will focus on delivering semi-automated tools to improve two areas of risk assessment and monitoring: Data provenance, improving trustworthiness of data ingestion, processing and linking, making sure it is compliant for research; and Privacy assessment, minimising the risk of identifiable information in clinical free-text records (e.g. GP letters, discharge summaries). Public involvement and engagement are central to our project, ensuring risks are properly identified and addressed, and our methods are transparent and understandable.Our collaborative approach will produce an implementable toolkit for all health data providers across the UK. This project offers significant benefits for data audit and release, improving consistency between organisations, access time for researchers and promoting access to data that has not been feasible before.

数据正在改变健康和社会保健，实现改变生活的发现，推进医疗保健服务，改善生活。然而，健康数据提供商在提取和链接这些复杂数据以及保护其安全发布以供研究方面面临挑战。风险评估对于确保数据发布不会构成隐私风险（例如包含可识别的患者信息或正确处理患者记录）至关重要。然而，目前这些治理过程是临时的、手动的、耗时的，可能会禁止数据发布，最终限制新的健康和社会护理创新。该项目将专注于提供半自动化工具，以改善风险评估和监测的两个领域：数据来源，提高数据摄取、处理和链接的可信度，确保其符合研究要求;和隐私评估，最大限度地减少临床自由文本记录（例如GP信件，出院摘要）中可识别信息的风险。公众的参与和参与是我们项目的核心，确保风险得到适当的识别和解决，我们的方法是透明和可理解的。我们的合作方法将为英国各地的所有健康数据提供者提供一个可实施的工具包。该项目为数据审计和发布提供了显着的好处，提高了组织之间的一致性，研究人员的访问时间，并促进了以前不可行的数据访问。