Data Innovations in Population Health Management

By: David F. Zirkle, PhD |

“Everything that can be invented has been invented.”  – Charles H. Duell, Director of US Patent Office 1899

Population health management is a concept that has been around for quite some time, although it has yet to be fully implemented in healthcare.  However, recent changes on many fronts have created incentives that may cause wider adoption of population health management concepts.

Population health management holds great potential for improving health outcomes and lowering costs, but significant obstacles still need to be overcome before the concept is fully realized.  This article outlines current approaches to population health management including data requirements, while future articles will discuss analytical techniques and potential applications.

Data, Data and More Data


Traditionally, hospitals and health systems have used inpatient metrics to assess their operational and financial performance.  However, managing the health of populations requires data beyond what is captured in internal discharge systems.  A broader view of care – from primary care to the post-acute care setting, is necessary to identify and manage the healthcare needs of a population.


Hospitals and health systems are now using claims data to better understand the health needs of a population.  Claims data offers an expanded view of a population with respect to health status and the continuum of care.  Common utilization metrics include hospital admissions, average length of stay, inpatient and outpatient costs, emergency room visits, prescription drug usage and primary care and specialist office visits.


Additionally, it is critical to evaluate the clinical risk of a population through the population’s clinical characteristics affecting healthcare utilization.  Clinical encounter data from electronic medical records as well as disease registries and case management files increases the richness of information available about individuals and the population overall.  Assessing risk profiles by disease state helps to understand how a population utilizes the health system and to identify key cost drivers.


The demographic makeup of a population can also have a significant impact on healthcare utilization and cost.  In addition to basic age and gender profiles, other demographic features such as geography, occupation, income, education level and socio-economic structure can have a profound effect on how best to manage the health of a given population.

Behavioral & Lifestyle

As organizations gain greater understanding of their consumers, they will need to develop criteria that assigns individuals to specific population cohorts.  A largely untapped source of information for population analysis is behavioral and lifestyle data.  Household demographics can be combined with other data sources to predict future healthcare needs and design proactive interventions.

Moving Forward

Health systems have always had access to a wealth of data. However, the information has historically been stored in data silos, limiting an integrated and meaningful analysis.  An emerging concept in data management is “big data.”  Big data is a broad term for data sets so large or complex that traditional storage and analytical techniques are inadequate.

With respect to population health management, big data involves aggregating all information relevant to an individual’s healthcare – including data traditionally housed in the organization as well as metrics collected from secondary sources outside of the organization.

A successful population health management program begins with an aggregation of all relevant data points and a thorough analysis that supports informed decision making.  Success will also include close monitoring and the flexibility to adapt to achieve the stated goals of the program.