Data Lakes and Data Visualization: An Innovative Approach to Addressing the Many Challenges of Health Workforce Planning

Denise D. Krause


Background: There are a variety of challenges to health workforce planning, but access to data is critical for effective evidence-based decision-making. Many agencies and organizations throughout Mississippi have been collecting quality health data for many years. Those data have historically resided in data silos and have not been readily shared. A strategy was developed to build and coordinate infrastructure, capacity, tools, and resources to facilitate health workforce and population health planning throughout the state.

Objective: Realizing data as the foundation upon which to build, the primary objective was to develop the capacity to collect, store, maintain, visualize, and analyze data from a variety of disparate sources -- with the ultimate goal of improving access to health care.

Specific aims were to:

1)  build a centralized data repository and scalable informatics platform,

2)  develop a data management solution for this platform and then,

3)  derive value from this platform by facilitating data visualization and analysis.

Methods: We designed and constructed a managed data lake for health data from disparate sources throughout the state of Mississippi. A data management application was developed to log and track all data sources, maps and geographies, and data marts.  With this informatics platform as a foundation, we use a variety of tools to visualize and analyze data.

Results: Samples of data visualizations that aim to inform health planners and policymakers are presented. Many agencies and organizations throughout the state benefit from this platform.

Conclusion: The overarching goal is that by providing timely, reliable information to stakeholders, Mississippians in general will experience improved access to quality care. 

Full Text:



Online Journal of Public Health Informatics * ISSN 1947-2579 *