Diabetic patients are hiding in plain sight

Diabetes is a complex and costly chronic disease. Studies estimate that diabetes affects 8% of the U.S. population, but confirming this in patients who are undiagnosed, and identifying those at highest risk, remains challenging. At Allscripts Analytics, we’re transforming insights from traditional electronic health record (EHR) data into innovative methods for early identification of chronic disease and population health management.

Variation in quality of diagnosis documentation within EHRs has necessitated development of new algorithms to more accurately define and manage our populations. After extensive data aggregation and normalization of clinical, claims, laboratory and pharmacotherapy data, our algorithms are validated on more than 40 million records to identify undiagnosed diabetic patients.

Advancements in visualization tools enable us to deliver insights from this data to our clients in a simple, interactive format in real-time. It helps clinicians better identify undiagnosed and at-risk diabetics, facilitate early intervention, address gaps in care and prevent disease progression.

Based on early data analysis, we’ve found that providers who only use traditional methods are identifying just 28% of their total diabetic population*.


                * Initial analysis of 4 million patients (single health system)

We have built upon the extensive work that Centers for Disease Control and Prevention (CDC) and other agencies have done measuring the geographical burden of disease from diabetics in the U.S. (check out the interactive map on CDC’s website). And we have the ability to geographically demonstrate the burden of disease from diabetes to our clients and their communities, in real-time.

Going beyond identification: Trends and predictive medicine

Once we have defined at-risk patients, we can begin to look at specific complex social and environmental risk factors that impact diabetes  that aren’t necessarily in the health data. For example, counseling a patient on diet modification is unlikely to help if your patient only has access to fast-food delivery because they can’t walk, or resides in a ‘food desert’ where fresh fruits and vegetables are unavailable. With targeted, informed interventions, patients can get treatment tailored to and relevant to their environments, which may include dietary advice, exercise programs or medication availability.

Understanding how patients have responded to treatment can help predict which patients are at greatest risk for developing retinopathy, stroke, heart disease or other complications from diabetes.

We are using historical insight from 40 million records in real populations to better understand pathogenesis of disease among different groups of people. If we can show positive patient results from 150,000 other diabetic patients with similar BMI, or race or age, we can empower people with understanding and responsibility for their own health.

Allscripts Analytics Population Health Analytics (PHA) can be integrated within the Allscripts dbMotion™ Solution to use aggregated and harmonized data from both inpatient and outpatient settings and deliver it back to the point of care for improved outcomes. Primary care providers can identify compliance with bi-annual HbA1c tests ordered by other providers from alternative facilities to eliminate redundant testing, identify true gaps in care, and comply with value-based care funding initiatives.

If you’d like to learn more about Allscripts Analytics PHA contact us.

Disease packages currently available through PHA:

  • Diabetes
  • Asthma
  • Coronary Artery Disease
  • Congestive Heart Failure
  • COPD
  • Hypertension

Tags: , , , , ,

About the author

Fatima Paruk, M.D., MPH, is the Chief Medical Officer at Allscripts Analytics. She provides medical leadership to a world-class team to develop, design and deploy predictive models to improve health. She is a physician and public health specialist that has been extensively involved in health systems and global surgical initiatives. She established Kenya’s injury surveillance system, has worked to identify gaps in care and promote hospital quality improvement. In addition to her executive role, Fatima remains committed to disaster response and recently authored Kenya’s National EMS policy.



Eric Quinones MD says:

12/30/2015 at 1:33 pm

Nice summary Fatima! I think the data speaks for itself when using traditional methods of identifying chronic Dz populations (28% for DM in the population that was evaluated). Uncovering the remaining population through other sources of data is key in order to truly appreciate what an organization is up against. Moving forward toward geographically teasing out where most of these populations reside, understanding their socioeconomic and environmental situations, lifestyle habits, customizing the right “care packages” for these people, and monitoring the progress to further circumvent Dz complications and fine tune with those still needing more attention is in line the Quadruple Aim. It is simply good care.

It would be interesting to find out if the converse is being done? What I mean is looking at the various data sources and identify patients who have been Dx with “X” [in their problem list] however do not have any supporting documentation, pharmacy data, lab/test results, radiological findings, claims data that support such a Dx. The applications of this tangent can be exceptional as well.

Be well, Eric


Your email address will not be published. Required fields are marked *