Monthly Archives: February 2014

The Buzz of Big Data and Analytics


Post by Dana Alexander, RN, FAAN


Chief Nursing Officer, Caradigm

Big Data can drive improvements in care processes, delivery and management. This is particularly important in today’s growing environment of risk sharing, fixed reimbursement and penalties incurred for not achieving expected quality and outcome benchmarks. We are in a time of value-based business models and value-based care. . . organizations need analytics to manage the higher level of risk and reward. Data that is transformed into meaningful information is essential, but the challenge for organizations is how to harness this data for purposeful use. Data analytics is necessary from the individual level to population health, with the ability to include not only acute care, but settings across the care continuum. The post-acute care settings are of particular focus as a way to manage care in a less costly but quality way, the latter becoming an important consideration in risk sharing and capitated models. The capability to blend and align clinical and financial data into analytics is particularly crucial with the risk-reward models that are in play. What may appear on the surface as reasons for increased costs and utilization of services may not be the true root cause.

As an example, Geisinger Health Plan had long-used clinical and financial data for population health management to identify opportunities for cost and quality improvements. Geisinger has learned that underlying factors such as “behavioral health” issues may be significant drivers in utilization of health care services. This is a proof point that data must be analyzed with an open and creative lens, as never before, to better manage care.

So what types of analytics are necessary? While retrospective reporting and comparative analytics are important, explorative analytics to investigate for root cause analysis can give insight to improve processes and care management. Of great value and of growing importance are analytics that are more near-real time, providing guided analytics translating insight into action. Guided analytics identifies a problem or risk situation such as a predictive risk score that alerts clinicians for awareness and decision making to take action Even more advanced are predictive analytics that allows for manipulation of variables and assumptions based on algorithms and “if and then” situations to forecast a future event and impact on outcomes. Last, prescriptive analytics based upon evidence can guide specific actions in managing individuals and population health. Evidence-based protocols continue to demonstrate the value to achieve quality and cost management goals, and with the right analytics, standards-based protocols can be customized to individuals to effectively achieve desired quality and performance goals.

It’s an exciting time in the world of Big Data. The possibilities for data analytics in healthcare to drive insights and take action are burgeoning. Unlike other industries that have been using analytics in a variety of ways with proven value, healthcare is relatively young in optimizing analytics for clinical and business intelligence to drive performance and forecast new business models. As healthcare systems take on the challenge of managing higher risk, Caradigm solutions are well positioned to support the emerging frontier of Big Data and analytics for today and the future.

Synthesis in Healthcare


Post by Ed Barthell, MD


Medical Director, Americas, Caradigm

(sin-thuh-sis), noun, plural – syntheses.   A complex whole formed by combining.

The world of medicine is full of activities that involve synthesis of data.  Every day doctors and nurses synthesize data from multiple sources as they care for patients.  They aggregate verbal data from the patient, the patient’s family, emergency medical technicians, care managers and other caregivers.  They combine this information with such things as data reports from laboratories, medication lists from pharmacies, notices from insurance companies, and imaging reports from free standing centers.  They synthesize this data with other information such as trends reported in medical studies involving similar patients, news reports and weather information.  And notice all of this data synthesis needs to occur in addition to reviewing the data available from various electronic medical record systems used by multiple providers involved in a given patient’s care.

Of course all of this data, even when available in electronic form, can be very difficult to aggregate, not to mention synthesize in an effective way to drive clinical and administrative decision making.  It is rare to find a health care worker who will not admit wasting time every day searching for data, even those who work with a supposedly comprehensive electronic health record system.  And I’m not proud to admit that in my own clinical practice I saw directly the impact of having to make decisions without knowing what I didn’t know, and subsequently seeing less than optimal outcomes.

I strongly believe the health care industry, like other big complex industries, is best served by a diverse range of systems that support ongoing rapid innovation, rather than dependence on a monolithic software system and a monopolistic business model.  But in a world of diverse systems, interoperability of those systems is needed, and aggregation of data from diverse systems is essential to enable data synthesis for various business purposes.

The Caradigm™ Intelligence Platform (CIP) was created as a robust solution to address this issue.  Now in its third generation as a commercial product, the platform includes state of the art tools that enable efficient ingestion and aggregation of data from multiple diverse source systems.  These tools provide a visual environment for mapping, interpreting and validating data, correctly matching data to patients, deriving calculated fields, applying predictive analytic algorithms, tagging to standardized terminology services, and grouping data into intelligent conceptual entities.

In turn, CIP surfaces that data through an open application framework for multiple uses, whether end user applications are built by Caradigm, customers or third-party partners.  All of these mechanisms allow CIP to “pre-position” data for further data synthesis by healthcare knowledge workers, so they can do their jobs with high efficiency and high quality.  Diverse data systems supporting innovation, and at the same time aggregating data to support data synthesis tasks by smart people, result in improved outcomes – pretty cool stuff!