Monthly Archives: May 2015

How to Get the Most Out of Population Health Analytics


Post by Sumeet Shrivastava


VP Engineering for Population Analytics, Caradigm

It seems like there is a constant buzz these days around healthcare analytics and their role in population health. It makes sense because in order to effectively manage a population of patients, healthcare organizations need to gain a variety of different insights. For example, they need to understand the clinical and financial risk of their population, define cohorts and prioritize patients to be enrolled in care management, evaluate how they are performing against quality measures, view patterns in utilization for financial improvement, etc. Analytics provide these insights.   

However, in order to get the most value from analytics, it’s important to understand how analytics are integrated with other population health strategies. Analytics shouldn’t be viewed as an independent activity because population health is a connected series of activities impacting the entire organization and requires a broad set of capabilities including data aggregation, analytics, care coordination and patient engagement and outreach.  It is also important to consider end user needs such as making it easy to access, visualize and take action. Let’s explore a few of the key success factors needed for population health analytics in more detail.

  • Quantity and quality of data: These elements are essential to light up any pop health analytics scenario. Across many organizations, I have seen implementations get delayed due to “bad data”, i.e. data that is not ingested in the format that is required to produce quality analytics, and later requires additional work to cleanse the data to be usable. A data aggregation solution should be designed to handle bad data and provide tooling to make it easier and faster to consume data from different and often non-uniform sources. While the data from different systems will be inherently non-uniform, data ingestion tooling and software should considerably shorten the process. Quantity i.e. completeness of data is also important because incomplete data dilutes the value of the insights presented. Incomplete data can skew or inflate insights, which then can make it challenging to formulate actionable strategies based on the information. 
  • Easy and real-time access: Once data has been aggregated and cleansed, it needs to be easily accessible, timely and in a format that can be used by both applications and by non-technical analysts. If it takes days or weeks to access analytics, then that time lag can render the data out- of-date.  Creating consistent and reusable data models along with self-service tools better ensures that queries are simple, maintainable and timely. 
  • Actionable insight: For analytics to make the greatest impact, they need to be actionable and integrated into clinician workflows. For example, gaps in care can be surfaced in an EMR so that a physician can close them while still in the presence of a patient. Also, if an analyst sees quality measures below where they should be, the analyst should be able to drill down to the provider and patient level so that additional action can be taken (e.g. enroll patient in a campaign or the analyst creates a task to prompt a clinician to take action). Analytics should also be surfaced within care management workflows as part of a longitudinal patient record so that all members of a care team have a more complete picture of patients, which can then be incorporated into the plan of care.
  • Flexible visualization engine: A picture is worth a thousand words. Users need to able to visualize the data in various formats – whether it is graphs, plots, trend lines, etc. An analytics engine should support different forms of visualizations that give users flexibility to derive value. 
  • Advanced analytics: To evolve beyond retrospective reporting and receive greater value from analytics, organizations need to leverage predictive and prescriptive analytics. Predictive analytics are essential for prioritizing resources as they forecast clinical risk, identify cost savings opportunities, likelihood of readmission, and can even identify which patients are likely to comply with a plan of care. Based on these predictions, prescriptive analytics can go one step further by suggesting interventions and identifying what actions should be taken to improve care for the patient.

Caradigm has taken a holistic approach to population health analytics since our inception.  We designed our enterprise data warehouse, analytics applications and workflow applications to work together, which makes each individual application more effective. Our analytics offering is unique because it can leverage virtually all of an organization’s data from disparate systems in real-time, apply best-of-breed algorithms to that data to derive insights, then surface that information directly within clinician workflows to drive action. If you’d like to discuss pop health analytics more, then please send us a note here. I look forward to continuing the discussion on analytics in an ongoing series of posts that will be coming from the Caradigm team. 

 

Rethinking the Business of Healthcare


Post by Brad Miller


Vice-President of Clinical Solutions, Caradigm

“What businesses are we in?” ask Michael Porter and Thomas Lee of the healthcare industry in their New England Journal of Medicine Perspective article entitled “Why Strategy Matters Now[.”[1]  As the entire healthcare spectrum transitions from a fee-for-service (FFS) paradigm to a more risk-based system, Porter and Lee contend that healthcare has entered a new era of strategic thinking and must employ new business approaches. I wholeheartedly agree that we need to start focusing on value in healthcare versus maximizing revenue.  

This new era in healthcare is marked for its focus on population health and patient-centric care to drive high value outcomes.  Porter and Lee believe that healthcare organizations should adopt new care concepts like the Integrated Practice Unit (IPU). Their IPU concept is based around specific diseases and comorbidities – like diabetes or asthma – rather than the traditional model of being department or provider-specialty centric.  This means that provider systems can truly focus on delivering disease and condition specific care across a population to achieve high value care. This concept would bring high quality practice and refinement to some of our sickest and highest utilizers, while also driving preventive care for those who have not converted to a full disease state. 

As the healthcare economy evolves in this risk-based direction, the IPU model (or a similar concept – patient-centric care across specific populations) will help break from the FFS “one size fits all” era.  It allows providers to focus not only on what they do well, but to provide a care environment for continual learning, discovery and refinement of care models and methodologies for their specific populations. There is also the possibility that IPUs can reduce large amounts of medical waste by standardizing best practices and reducing unnecessary or redundant tests and procedures. 

Simultaneously, there is a manifestation resulting from the physician and nurse education models that aligns with this disruption in the traditional healthcare business model. Predominantly, in the late 1980s and 1990s many medical schools switched to systemic-based curricula vs organ and departmental approaches.  I know this was the case at Weill Cornell, where I went, and at many of the other medical schools where my colleagues went with whom I have discussed their curricula.  From a learning standpoint, our generation of physicians were taught to view the body more as a system, rather than isolated organs. This generation of physicians are now in leadership roles at healthcare entities, ready to bring a more holistic perspective to the practice of medicine and healthcare.

It reminds me of the Apple Computer strategy of focusing on the educational market in the 80s and 90s – seeds planted a decade or two ago that helped create Apple brand loyalty and the foundation for making computing so central to our lives today. 

We are in an era of transformation as evidenced by the Affordable Care Act (ACA), the removal of Sustainable Growth Rate (SGR) for Medicare, Centers for Medicare and Medicaid Services (CMS’) rapid focus on risk-based payment models, and private businesses directly contracting for care with health systems in growing numbers (private ACOs, bundled payments, etc.). While we might not know exactly where the future will move healthcare, many signs point to it being risk-based and an era of rapid evolution and adaptation. In my experience with ONC’s Beacon Program and various providers under the CMS Innovation program, creating a clinical care environment that can easily adapt on top of a solid data and IT infrastructure is critical to supporting providers in this new and changing world.  Deep intelligence into a provider’s patient population, financial and clinical risk among other information and technical requirements will become central in this healthcare evolution.  I’ll tackle that technical aspect in my next blog post. In the meantime, check out Porter and Lee’s piece on the rapidly shifting sands of healthcare business strategy.



[1] Porter, Michael E and Lee, Thomas H. “Why Strategy Matters Now” New England Journal of Medicine. April 30, 2015.Publsihed from http://www.nejm.org/doi/full/10.1056/NEJMp1502419

How Population Health Enriches the Patient Record


Post by Sameer Bade, MD


Vice President of Clinical Solutions, Caradigm

As providers seek new capabilities to help them in their journey to population health, one of the first items they usually target is analytics. Analytics are undoubtedly an important piece of a population health strategy, however, this is just one of a number of important capabilities providers must obtain. In my experience collaborating with providers, a sometimes overlooked capability is creating and sharing a comprehensive, enriched longitudinal patient record. With the shift from physician-focused, episodic-care to team-based care involving multiple clinicians and care givers, it has become essential to have a real-time, 360 degree view of the patient that is shared among the entire team. With that enriched view, a care team can more effectively and efficiently deliver coordinated and proactive patient-centered care that drives improved outcomes. Let’s explore this issue in greater detail.

The reality is that clinical information from a single electronic health record (EHR) provides only a small portion of the information needed for population health management. If there are multiple EHR’s in a clinically integrated network, clinical data for patients may be siloed in disparate EHRs. Also absent from patient records are numerous other key pieces of information such as:

  • Claims data (e.g. services obtained, medications, etc)
  • Care plans
  • Lab results
  • Patient outreach information
  • Patient submitted / supplied information (biometrics, logs/journals, preferences, etc.)
  • Predictive analytics such as a readmissions risk score, clinical risk, forecasted cost, etc.
  • Analytics that measure medication compliance
  • Gaps in care/quality measures that need to be closed
  • Important non-clinical information (e.g. patient motivation, family support team members, life events such as a recently deceased spouse, and other social factors)

Enriching the patient record with this information enables a depth of patient understanding required to support the transformation to value-based care. Here are a few examples of how the enriched patient record can have an impact.

Scenario 1

With pharmacy benefits claims data automatically augmenting the patient record, a care manager can quickly see which prescriptions have been filled without having to log into multiple systems. They can complete a medication review faster and more accurately and can share this with the care team. It is well known that improper or inadequate medication management can  play a major factor in readmissions and complications (shown to cause as much as 20 percent of hospital readmissions[1]). However, having just EHR based medications (list or prescriptions) and pharmacy benefit / fill data is not enough. Being able to capture what the patient is actually taking can provide enhanced insight.  After medication review, a care manager can determine that a pharmacist needs to be added to the care team to help manage dosing regimens and timing of medications. The care manager can then assign a task to the appropriate care team member working at top of license to make arrangements with the pharmacist and add a note to the patient record that is shared with all other care team members. 

While completing medication review, a care manager may also discover life events that are barriers to medication compliance such as an inability to pay for medications, not having transportation to pick them up, or patterns such as sharing/splitting doses with a spouse. The care manager can then assign a task to an appropriate care team member to make transportation services arrangements for the patient or enroll them in an financial assistance program, and add another note to the patient record that is shared with all other care team members. 

Scenario 2

The same high-risk patient described above goes to see a primary care physician who is part of a clinically integrated network. When the physician looks up the patient’s record in their own EHR, the enriched longitudinal information and actions taken in Scenario 1 are carried forward to the point of care. In this scenario, the physician or nurse can have a deeper and more informed conversation with the patient about medication compliance. Furthermore, easy access to a  comprehensive, validated medication review as part of the enriched longitudinal record, can help speed up the medication reconciliation process in the clinic. With full context on the patient that also includes all care programs they are enrolled in, lab results, visits history, readmissions risk score and relevant patient documents such as a care plan, the provider is better equipped to evaluate and direct additional care. Simultaneously, the provider can also see gaps in care and quality measures (e.g. need for a depression screening) that can be closed while the patient is still in the clinic. From a patient perspective, the provider’s enhanced understanding of issues and plan of care can improve the overall experience. The physician can even see what motivates the patient (perhaps the care manager noted that the patient has a goal to be able to attend their grand daughter’s college graduation) and encourage continued participation.

In the big picture, successful population health management requires addressing a population of patients as individuals. An enriched longitudinal patient record as described here can help providers gain a better understanding of their patients and enable the care team to be more effective, efficient, coordinated and patient-centered.

To learn more about how your organization can obtain and share a longitudinal patient record across a care team, send us a note here to schedule a discussion. 



[1] Guitierrez, David. “Drug Side Effects Blamed for 20 Percent of Hospital Readmissions.” Posted from http://www.naturalnews.com/027866_drugs_side_effects.html# 1.4.10.