Chao Kang, Sarker Md Nazirul Islam, Ali Isahaque, Firdaus R B Radin, Azman Azlinda, Shaed Maslina Mohammed
School of Economics and Management, Neijiang Normal University, Neijiang, 641199, China.
School of Social Sciences, Universiti Sains Malaysia, USM, Pinang, 11800, Malaysia.
Heliyon. 2023 Aug 31;9(9):e19681. doi: 10.1016/j.heliyon.2023.e19681. eCollection 2023 Sep.
The use of healthcare data analytics is anticipated to play a significant role in future public health policy formulation. Therefore, this study examines how big data analytics (BDA) may be methodically incorporated into various phases of the health policy cycle for fact-based and precise health policy decision-making. So, this study explores the potential of BDA for accurate and rapid policy-making processes in the healthcare industry. A systematic review of literature spanning 22 years (from January 2001 to January 2023) has been conducted using the PRISMA approach to develop a conceptual framework. The study introduces the emerging topic of BDA in healthcare policy, goes over the advantages, presents a framework, advances instances from the literature, reveals difficulties and provides recommendations. This study argues that BDA has the ability to transform the conventional policy-making process into data-driven process, which helps to make accurate health policy decision. In addition, this study contends that BDA is applicable to the different stages of health policy cycle, namely policy identification, agenda setting as well as policy formulation, implementation and evaluation. Currently, descriptive, predictive and prescriptive analytics are used for public health policy decisions on data obtained from several common health-related big data sources like electronic health reports, public health records, patient and clinical data, and government and social networking sites. To effectively utilize all of the data, it is necessary to overcome the computational, algorithmic and technological obstacles that define today's extremely heterogeneous data landscape, as well as a variety of legal, normative, governance and policy limitations. Big data can only fulfill its full potential if data are made available and shared. This enables public health institutions and policymakers to evaluate the impact and risk of policy changes at the population level.
预计医疗保健数据分析的应用将在未来公共卫生政策制定中发挥重要作用。因此，本研究探讨如何将大数据分析（BDA）系统地纳入卫生政策周期的各个阶段，以进行基于事实的精准卫生政策决策。所以，本研究探索了BDA在医疗行业准确、快速决策过程中的潜力。使用PRISMA方法对22年（从2001年1月至2023年1月）的文献进行了系统回顾，以构建一个概念框架。该研究介绍了BDA在医疗政策方面的新兴主题，阐述了其优势，提出了一个框架，列举了文献中的实例，揭示了困难并提供了建议。本研究认为，BDA有能力将传统决策过程转变为数据驱动的过程，这有助于做出准确的卫生政策决策。此外，本研究认为BDA适用于卫生政策周期的不同阶段，即政策识别、议程设定以及政策制定、实施和评估。目前，描述性、预测性和规范性分析被用于基于从几个常见的与健康相关的大数据源（如电子健康报告、公共卫生记录、患者和临床数据以及政府和社交网站）获取的数据进行公共卫生政策决策。为了有效利用所有这些数据，有必要克服定义当今极端异构数据格局的计算、算法和技术障碍，以及各种法律、规范、治理和政策限制。只有在数据可用且共享的情况下，大数据才能充分发挥其潜力。这使公共卫生机构和政策制定者能够在人群层面评估政策变化的影响和风险。
