Achieving Value in Population Health Big Data

Several population health big data projects have been initiated in the USA recently. These include the County Health Rankings & Roadmaps (CHR) initiated in 2010, the 500 Cities Project initiated in 2016, and the City Health Dashboard project initiated in 2017. Such projects provide data on a range of factors that determine health—such as socioeconomic factors, behavioral factors, health care access, and environmental factors—either at the county or city level. They provided state-of-the-art data visualization and interaction tools so that clinicians, public health practitioners, and policymakers can easily understand population health data at the local level. However, these recent initiatives were all built from data collected using long-standing and extant public health surveillance systems from organizations such as the Centers for Disease Control and Prevention and the U.S. Census Bureau. This resulted in a large extent of similarity among different datasets and a potential waste of resources. This perspective article aims to elaborate on the diminishing returns of creating more population health datasets and propose potential ways to integrate with clinical care and research, driving insights bidirectionally, and utilizing advanced analytical tools to improve value in population health big data.