转型总监Justin Hassall Informed Solutions
数据的使用处于世界抗击为期两年的全球大流行病的最前沿. The advances in data analytics using data collected from a large proportion of the population through COVID-19 again showed the potential for data platforms to address long-term challenges vital to the future of health and social care.
机会(和挑战)的规模可以在 Goldacre报告的 十大网博靠谱平台在医疗保健环境中更好地利用数字技术和数据的185项广泛建议. This report flags critical data privacy and inclusion issues and although there are huge opportunities for better use of data, 在收集和使用患者数据时也迫切需要谨慎和考虑. 这必须以提供个人信息访问的道德框架为指导, 以及旨在减少医疗保健获取和提供不平等的系统.
加快提供人人享有的保健服务
在医院之外的不同护理环境中,加速提供护理的需求正在不断发展, driven by a public demand for access to care in environments most appropriate to individuals and their specific needs.
然而, 而一些护理人员, 当地政府, 而其他组织则是数据使用方面的开拓者, 数字工具和技术, 社会关怀落后. 在这一卫生服务和护理途径的新愿景中,提高数据质量至关重要, 作为卫生部的名称 & 社会关怀战略在其2022年战略中指出 数据拯救生命.
Underpinning any transition to an intelligence-led health service is the need for the 交换 of high-quality data, using information transferred within and between Integrated Care Systems (ICSs) to make vital decisions about what care is delivered and where.
数据对于确保正确的人在正确的时间和正确的地点获得正确的护理至关重要. It’s a key ingredient for organising care and joining up health and social care services around people’s abilities and needs. It’s also a central ingredient for improving population health and care; which is key to tackling healthcare disparities, 不平等的结果, and access; and a catalyst for driving healthcare productivity and value for money.
建立信心和信任
确保高水准的数据质量, 公众需要更自如地分享和提供个人信息. 这种安慰和信任来自于建立自信的方式,他们的敏感, 分享个人资料, 储存和使用,以便简化和加速他们获得所需的护理和治疗. 如果数据不准确或“决策等级”,那么它的能力就会大大降低.
将患者置于数据收集和准确性挑战的中心是很重要的, 但这必须有效地完成. 2020年11月, The Department of Health and Social Care published a report on excessive bureaucracy in the health and social care system, 哪些证据性数据收集直接影响医疗服务的提供. 错误的人,做错误的工作,但有正确的理由. 虽然不质疑高质量数据的重要性, this also serves as a warning that data collection must be efficiently designed into processes so as not to damage the care it seeks to improve.
The mapping of demographics and where people live has led to the ability to geographically plan and place services and care where it is most needed, 建立模型以了解队列的结构和规模, 例如提供疫苗接种或提供药物以减轻局部疾病暴发.
随着综合护理系统(ics)成为现实,作为NHS长期计划的重要组成部分, 需要确保数据和信息在中央之间方便安全地流动, 区域, 当地的护理机构也至关重要. NHS并不缺乏数据,但它确实受到来自多个来源的孤立数据的困扰.
The global health care sector was already using new technologies and processes to extend care delivery outside the hospital setting when COVID-19 forced providers to transform operations overnight and dramatically adopt virtual consultations, 访问, 远程病人监护.
患者参与和护理服务的强制转变带来了许多机会和好处, not least the potential to deliver physical and virtual care in a meaningful and integrated way that delivers better patient experiences and better clinical outcomes regardless of where patients are.
集成钥匙
使这一愿景成为有效的现实, NHS和整个供应商社区必须提供整合, 协作, 沟通, and information sharing needed to serve the needs of the whole population and a growing body of patients that require care in remote settings - receiving care where they need it most, 以及他们的需求最能得到满足的地方. This care will be delivered by multi-disciplinary teams collaborating remotely to deliver a whole system approach to care throughout communities.
现有的NHS的碎片化和分化程度, 互操作性仍然是新型数字化综合护理服务的基本组成部分. 当与向物理病房外提供护理相抵触时, our view is that both data quality and data sharing platforms should not merely be defined by the available technology, 而是根据病人的需要, 临床医生, 以及更广泛的健康和社会关怀社区.
真正有效的互操作性生态系统将提供使用技术标准的统一基础设施, 政策, 以及实现无缝安全捕获的协议, 发现, 交换, 健康信息的利用, 有适当的控制,以确保正确和有效的使用. 在这, the reshaping of legacy systems with platforms that talk to each other and work better together will be used to more effectively access and share data.
这个生态系统还必须更好地应对共享非结构化数据的挑战, 例如采用人工智能(AI), 机器学习(ML), 和自然语言处理(NLP)技术来发现和提供相关的信息在使用点. 然而, to meet this challenge the development of new data science models must come hand-in-hand with an improvement of the quality, 可用性, 并适当使用数据集来解释种族, 性别, 以及社会的多样性和平等.
实现梦想
作为两届女王奖创新获奖者,我们有能力加速和降低数字业务变革的风险, we see several keys to the challenge of data quality across the NHS estate including addressing data validation and support for the cleansing, 地址数据的匹配和验证. 使用机器学习来提高人口统计数据质量的潜力是显而易见的, leading to better management of data quality streams including the cleansing and auto-correcting of huge swathes of demographics data.
成功解决信息质量问题,使卫生服务部门能够获得决策级数据, we also see through our work with NHS England (NHSE) on the national Learn from Patient Safety 事件 (LFPSE) service, 工业签署FHIR等技术标准的重要性, which is already having a significant and positive impact on the efficient sharing of learning and improved care delivery.
这就把我们带回到本文的开头——加速医疗服务的提供, 是什么在医院之外的不同护理环境中不断发展, is being driven by the demand for access to care in environments most appropriate to individuals and their specific needs. 没有围墙的医院和社会护理——为每个人服务. 质量、决策、等级数据是实现这一承诺的关键.