Healthcare News & Insights

Combining claims, EHR data creates a Rosetta Stone for population health

Healthcare organizations have massive amounts of data to share with payors and vice versa, to provide a timely, accurate picture of patients™ health status and care gaps. Problem is many issues hinder the sharing of these data sets. In this guest post, Eileen Cianciolo, chief product officer for a company that provides healthcare analytics solutions and services globally, details what needed to combine these two types of data sets for a new level of clarity around patient care.


The 1799 discovery of the Rosetta Stone was a major turning point in humanity ability to understand ancient Egyptian hieroglyphs. The additional data points of an exact translation in two known languages filled in knowledge gaps around hieroglyphs, unlocking many ancient texts that had previously been undecipherable.

Population health management (PHM) has had many similar limitations. Healthcare organizations hold massive amounts of patient data within their electronic health records (EHRs), but that data only covers care that has been delivered within their own system, practice or institution. As a result, they may not know when care gaps have been filled by other providers, which means any risk profiles they develop may be inaccurate.

Claims data from payors does offer a view of all care delivered throughout the continuum. But there is typically a three-month lag between care delivery and claims data becoming visible. Here again, what appear to be care gaps may have been filled elsewhere during that lag, which means a provider may end up wasting time, resources and money that could have been devoted to helping other patients. Additionally, since claims data doesn typically include biometrics it doesn offer deeper, more specific insights into a patient health status that can affect treatment, especially around chronic conditions.

The Rosetta Stone for PHM is combining both types of data to enable healthcare organizations to take advantage of the strengths of each while overcoming their limitations, creating a more timely and accurate picture of the patient health status and care gaps. Healthcare organizations can then use this information to prioritize the patients with the highest risk scores and assign their limited care management resources where they can deliver the greatest benefits. When socioeconomic, psychographic, and other data that shows who patients are, how they live, and what motivates them is added, the insights become even more on-target.

Getting there requires having a strong data strategy driven by robust, next-generation analytics that aggregate the data and build a more complete, longitudinal view of each patient current health, risk and cost profile. Comparing these profiles against pre-built personas that classify patients with similar attributes enables the organization to develop an impactability score for each. Placing these scores into a dashboard makes it easy to understand which patients are experiencing care gaps, as well as the impact of closing those gaps.

The result is a new level of clarity around care. Healthcare organizations will understand the clinical and financial impact of dedicating care management resources to certain areas, such as recommending a weight management program for a patient who has chronic hypertension and a body mass index above acceptable levels. They will also know where not to dedicate resources to closing care gaps because they will make little difference. Good examples are areas where the evidence shows closing those care gaps is never effective or has little to no effect on a patient health outcomes or a provider cost avoidance.

Guiding the transition to value

Analytics that combine clinical and claims data can also be instrumental in helping healthcare organizations understand financial factors that affect the transition to value-based care.

They can see the amount the organization is being paid to manage at-risk populations, helping executive management set priorities for improvement and understand whether current investments are delivering the projected results. Embracing predictive analytics can help the organization determine whether the effect of proposed changes will be positive or negative, while prospective analytics offer guidance on which of several potential courses the organization should follow.

The analytics can help improve resource utilization by population and facility as well. For example, if one hospital is seeing higher-than-average numbers of asthma patients in the emergency department, the organization may decide to dedicate more resources to education and prevention to reduce its risk exposure. They may even want to segment the asthmatic population into cohorts, so they can focus first not only on those with the greatest risk and impactability but also on the care gaps that should be closed first to achieve the greatest clinical and financial outcomes.

A revelation

The Rosetta Stone was a huge difference-maker not only in our understanding of early Egyptian writing but in the history of humanity.

Similarly, combining clinical, claims and additional non-traditional data through robust, prescriptive analytics can create new revelations for PHM around closing care gaps and hitting value-based outcome targets. It the answer key to improving outcomes and efficiency, increasing quality, reducing costs, managing provider and network utilization more effectively, and ultimately succeeding in the transition to value-based care.

Eileen Cianciolo is chief product officer with

Subscribe Today

Get the latest and greatest healthcare news and insights delivered to your inbox.