Medical Informatics Group, Center of Health Data Science, Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117, Berlin, Germany.
Berlin Institute of Health at Charité - Universitätsmedizin Berlin, Charitéplatz 1, 10117, Berlin, Germany.
BMC Med Inform Decis Mak. 2024 Nov 11;24(1):333. doi: 10.1186/s12911-024-02748-0.
Clinical data warehouses provide harmonized access to healthcare data for medical researchers. Informatics for Integrating Biology and the Bedside (i2b2) is a well-established open-source solution with the major benefit that data representations can be tailored to support specific use cases. These data representations can be defined and improved via an iterative approach together with domain experts and the medical researchers using the platform. To facilitate these discussions, it is important to understand how users interact with the system.
The objective of this work was to develop metrics for describing user interactions with clinical data warehouses in general and i2b2 in particular. Moreover, we aimed to develop a dashboard featuring interactive visualizations that inform data engineers and data stewards about potential improvements.
We first identified metrics for different data usage dimensions and extracted the relevant metadata about previous user queries from the i2b2 database schema for further analysis. We then implemented associated visualizations in Python and integrated the results into an interactive dashboard using Dash.
The identified categories of metrics include frequency of use, session duration, and use of functionality and features. We created a dashboard that extends our local i2b2 data warehouse platform, focusing on the latter category, further broken down into the number of queries, frequently queried concepts, and query complexity. The implementation is available as open-source software.
A range of metrics can be derived from metadata logged in the i2b2 database schema to provide data engineers and data stewards with a comprehensive understanding of how users interact with the platform. This can help to identify the strengths and limitations of specific instances of the platform for specific use cases and aid their iterative improvement.
临床数据仓库为医学研究人员提供了对医疗数据的协调访问。Informatics for Integrating Biology and the Bedside(i2b2)是一个成熟的开源解决方案,其主要优势在于可以根据特定用例定制数据表示。这些数据表示可以通过与领域专家和使用该平台的医学研究人员一起进行迭代定义和改进。为了促进这些讨论,了解用户如何与系统交互非常重要。
这项工作的目的是开发描述用户与临床数据仓库(特别是 i2b2)交互的指标。此外,我们旨在开发一个具有交互式可视化功能的仪表板,为数据工程师和数据管理员提供有关潜在改进的信息。
我们首先确定了不同数据使用维度的指标,并从 i2b2 数据库架构中提取了关于以前用户查询的相关元数据,以便进一步分析。然后,我们在 Python 中实现了相关的可视化,并使用 Dash 将结果集成到一个交互式仪表板中。
确定的指标类别包括使用频率、会话持续时间以及功能和特性的使用。我们创建了一个仪表板,扩展了我们的本地 i2b2 数据仓库平台,重点关注后者类别,进一步细分为查询数量、经常查询的概念和查询复杂性。该实现可作为开源软件使用。
可以从 i2b2 数据库架构中记录的元数据中得出一系列指标,为数据工程师和数据管理员提供对用户与平台交互的全面了解。这有助于确定特定用例的平台特定实例的优势和局限性,并帮助他们进行迭代改进。