Feinberg School of Medicine, Northwestern University, Chicago, USA.
AMIA Annu Symp Proc. 2022 Feb 21;2021:1208-1214. eCollection 2021.
The digitalization of the healthcare systems has resulted in a deluge of big data and has prompted the rapid growth of data science in medicine. Many informatics tools, such as data science, which is the field of study dedicated to the principled extraction of knowledge from complex data, can also introduce benefits into implementation science, quality improvement (QI), and primary care research. The increased amount of primary care QI initiatives, availability of practice facilitation-related data, the need for better evidence-based care, and the complexity of challenges make the use of data science techniques and data-driven research particularly appealing to primary care. Recent advances in the usability, applicability, and interpretability of data science models offer promising applications to implementation science. Despite the increasing number of studies and publications in the field, thus far there have been few examples of combining informatics and implementation framework to facilitate primary care studies. We designed and developed an informatics-driven implementation research framework to provide a coherent rationale and justification of the complex interrelationships among features, strategies, and outcomes. The proposed framework is a principle-guided tool designed to improve the specification, reproducibility, and testable causal pathways involved in implementation research projects in primary care settings.
医疗系统的数字化导致了大数据的泛滥，并促使医学领域的数据科学迅速发展。许多信息学工具，如数据科学，它是致力于从复杂数据中提取知识的原则的研究领域，也可以为实施科学、质量改进（QI）和初级保健研究带来益处。初级保健 QI 计划的数量增加，实践促进相关数据的可用性，对基于更好证据的护理的需求以及挑战的复杂性使得数据科学技术和数据驱动的研究对初级保健特别有吸引力。数据科学模型在可用性、适用性和可解释性方面的最新进展为实施科学提供了有前途的应用。尽管该领域的研究和出版物数量不断增加，但迄今为止，很少有将信息学和实施框架结合起来以促进初级保健研究的例子。我们设计和开发了一个信息学驱动的实施研究框架，以提供一个连贯的理由和说明特征、策略和结果之间复杂的相互关系。所提出的框架是一个原则导向的工具，旨在提高初级保健环境中实施研究项目中涉及的规范、可重复性和可测试的因果关系。
