Using Big Data to Find Hypertension Patients ‘Hiding in Plain Sight’ | David Raths | Healthcare Blogs Skip to content Skip to navigation

Using Big Data to Find Hypertension Patients ‘Hiding in Plain Sight’

June 19, 2017
| Reprints
AMGA Analytics compares members’ EHR data to CDC prevalence estimator

When we think about big data, we often picture it being used to address new challenges such as pharmacogenomics. It’s nice to remember that there are big data efforts tied to something relatively simple, like making sure patients get their blood pressure taken.

Last week I had a conversation with John Cuddeback, M.D., Ph.D., chief medical informatics officer for AMGA Analytics, a subsidiary of the American Medical Group Association. He described the process involved in combing through claims and EHR data to find patients with undiagnosed hypertension who are “hiding in plain sight.”

AMGA’s Analytics for Improvement (A4I) is a learning collaborative of its member practices working on population health improvement. The providers use the Optum One analytics platform. Leveraging the data, AMGA Analytics describes its work as creating analyses looking at the relationships among care processes, clinical outcomes and cost.

In its work on catching undiagnosed hypertension, AMGA Analytics took advantage of a prevalence estimator created by the Centers for Disease Control. Using the National Health and Nutrition Examination Survey (NHANES), CDC created a hypertension prevalence estimator that provider organizations and public health agencies can use if they know the demographics of their patient population, “The question for a provider organization is, ‘are we missing the diagnosis of hypertension on any of our patients?” Cuddeback said. “That is an important concept in the Million Hearts program as it was in our hypertension collaborative, called Measure Up, Pressure Down.”

The hypertension estimator uses four ranges of age, sex, race and ethnicity, and a number of conditions that are often related to hypertension — diabetes, obesity and chronic kidney disease. The assumption is there may be some patients for whom you are missing the hypertension diagnosis, Cuddeback said. “It is a diagnosis that involves a little judgment. People say, ‘Oh, your blood pressure seems a little elevated. Maybe it is just white coat hypertension.’ They often don’t follow up on the process. That is the concern.”

One of the questions they sought to address is how well the co-morbid conditions are picked up in the claims and EHR data. Although diabetes is diagnosed reasonably well, obesity is not, Cuddeback said. Of 8.9 million patients who qualified for this study, 7 million don’t have any of the co-morbid conditions diagnosed if you look at just one year’s claims data.

“We are recognizing that obesity very seldom appears on a claim compared to how often it is an issue for the patient,” he said. “You would think if we went to the EHR problem list, and did a five-year look-back we would pick up quite a few more, but it turns out that looking at the patient’s problem list doesn’t pick up many more patients.”

It is only when you use the clinical data from the EHR, the BMI score and other clinical data that might reveal diabetes in a patient who doesn't have it diagnosed, that you really begin to get a larger proportion of your patients, he said. Using the five-year look-back at EHR clinical data, more than half of the patients have one, two or three of those chronic conditions. “One of the points we are making is to characterize how many additional patients you get with these co-morbid conditions, depending on which data set you look at,” he said.

I asked Cuddeback if that tells us something about how physicians use the problem list.

“I am afraid it does,” he said. “They are doing pretty well at using the problem list for diabetes, but much less well for obesity. That is one of the big issues about obesity: It doesn’t get a lot of visibility or attention clinically. That is why we are beginning a three-year learning collaborative on obesity. As we surveyed members, they said they don’t really know how to even begin the conversation or what type of program to put together.”

Cuddeback sought to look at how well the participating AMGA members are doing at diagnosing hypertension. “We want to compare the estimated prevalence with the actual prevalence.”

They included patients who didn’t have a diagnosis, but had a stage two blood pressure reading (systolic pressure is 160 mm Hg or higher or diastolic pressure is 100 mm Hg or higher) recorded on at least one day over the past five years or stage one reading (140 to 159 mm Hg or a diastolic pressure ranging from 90 to 99) two days over the past five years.

By including those patients, they got percentages that were well above the highest estimate you would get from the CDC estimator.

Cuddeback and Vaishali Joshi, an AMGA Analytics senior data analyst, are now drilling down on the data from individual medical groups looking for explanations. “We could call these people up and tell them we have an estimator that we applied it to your data, and you don’t seem to be diagnosing hypertension as much as you should be. But that is not terribly useful to them,” Cuddeback said. “We have to be more specific.”

“As we look at individual groups, we want to see if there is a site of care where the pattern may be different in terms of hypertension evidence,” Joshi said. At some of the groups, there is more evidence of stage 2 blood pressure readings but no diagnosis or problem list mention. Maybe the patient only came for one visit or two. What age group are those patients? Are they on Medicare? “That is the kind of drill-down we are working on now,” she said.

There are still specialists who don’t see doing blood pressure screenings as their responsibility. Cuddeback said a physician such as a breast cancer surgeon isn’t expected to manage their patients’ blood pressure, but she is expected to check it on visits and refer them on so it can get managed.

He said AMGA is interested in working further with the CDC team “because they are so interested in taking granular data like this and producing examples of finding patients who are hiding in plain sight. We have the clinical evidence, but they are not getting into a registry because it is not documented in a problem list or a claim. The providers are not getting credit for it in terms of risk adjustment and the patients are not getting the benefit of disease management program the organization has.”

One thing the industry will have to grapple with as it works more with big data is the growth of machine learning, Cuddeback added. Traditionally predictive analytics have used conventional logistic regression modeling and clinicians bought in to the model at least in part because they knew what the coefficients were. They could see how the model worked.

“The problem with machine learning is that those models don’t tell you how they are working inside,” he said. “The meta-issue for healthcare is going to be getting people comfortable with machine learning models that are better at prediction, but we can’t as easily explain how they work.”

 

 

 

 

The Health IT Summits gather 250+ healthcare leaders in cities across the U.S. to present important new insights, collaborate on ideas, and to have a little fun - Find a Summit Near You!


/blogs/david-raths/population-health/using-big-data-find-hypertension-patients-hiding-plain-sight
/news-item/population-health/ncqa-moves-population-health-sphere-two-new-programs

NCQA Moves Into the Population Health Sphere With Two New Programs

December 10, 2018
by Mark Hagland, Editor-in-Chief
| Reprints
The NCQA announced on Monday that it was expanding its reach to encompass the measurement of population health management programs

The NCQA (National Committee for Quality Assurance), the Washington, D.C.-based not-for-profit organization best known for its managed health plan quality measurement work, announced on Dec. 10 that it was expanding its reach to encompass the population health movement, through two new programs. In a press release released on Monday afternoon, the NCQA announced that, “As part of its mission to improve the quality of health care, the National Committee for Quality Assurance (NCQA) is launching two new programs. Population Health Program Accreditation assesses how an organization applies population health concepts to programs for a defined population. Population Health Management Prevalidation reviews health IT solutions to determine their ability to support population health management functions.”

“The Population Health Management Programs suite moves us into greater alignment with the focus on person-centered population health management,” said Margaret E. O’Kane, NCQA’s president, in a statement in the press release. “Not only does it add value to existing quality improvement efforts, it also demonstrates an organization’s highest level of commitment to improving the quality of care that meets people’s needs.”

As the press release noted, “The Population Health Program Accreditation standards provide a framework for organizations to align with evidence-based care, become more efficient and better at managing complex needs. This helps keep individuals healthier by controlling risks and preventing unnecessary costs. The program evaluates organizations in: data integration; population assessment; population segmentation; targeted interventions; practitioner support; measurement and quality improvement.”

Further, the press release notes that organizations that apply for accreditation can “improve person-centered care… improve operational efficiency… support contracting needs… [and] provide added value.”

Meanwhile, “Population Health Management Prevalidation evaluates health IT systems and identifies functionality that supports or meets NCQA standards for population health management. Prevalidation increases a program’s value to NCQA-Accredited organizations and assures current and potential customers that health IT solutions support their goals. The program evaluates solutions on up to four areas: data integration; population assessment; segmentation; case management systems.”

 

 

More From Healthcare Informatics

/webinar/can-informatics-drive-clinical-quality-improvements-alongside-operational-improvements

Can Informatics Drive Clinical Quality Improvements Alongside Operational Improvements in Cancer Care?

Thursday, December 13, 2018 | 3:00 p.m. ET, 2:00 p.m. CT

Due to the complexity of the disease biology, rapidly increasing treatment options, patient mobility, multi-disciplinary care teams, and high costs of treatment - informatics canplay a more substantial role in improving outcomes and reducing cost of cancer care.

In this webinar, we will review how tumor board solutions, precision medicine frameworks, and oncology pathways are being used within clinical quality programs as well as understanding their role in driving operational improvements and increasing patient retention. We will demonstrate the requirements around both interoperability and the clinical depth needed to ensure adoption and effective capture and use of information to accomplish these goals.

Related Insights For: Population Health

/article/population-health/dc-department-health-care-digging-data-issues-collaborate-across

At the D.C. Department of Health Care Finance, Digging into Data Issues to Collaborate Across Healthcare

November 22, 2018
by Mark Hagland, Editor-in-Chief
| Reprints
The D.C. Department of Health Care of Finance’s Kerda DeHaan shares her perspectives on data management for healthcare collaboration

Collaboration is taking place more and more across different types of healthcare entities these days—not only between hospitals and health insurers, for example, but also very much between local government entities on the one hand, and both providers (hospitals and physicians) and managed Medicaid plans, as well.

Among those government agencies moving forward to engage more fully with providers and provider organizations is the District of Columbia Department of Health Care Finance (DHCF), which is working across numerous lines in order to improve both the care management and cost profiles of care delivery for Medicaid recipients in Washington, D.C.

The work that Kerda DeHaan, a management analyst with the D.C. Department of Health Care, is helping to lead with colleagues in her area is ongoing, and involves multiple elements, including data management, project management, and health information exchange. DeHaan spoke recently with Healthcare Informatics Editor-in-Chief Mark Hagland regarding this ongoing work. Below are excerpts from that interview.

You’re involved in a number of data management-related types of work right now, correct?

Yes. Among other things, we’re in the midst of building our Medicaid data warehouse; we’ve been going through the independent validation and verification (IVV) process with CMS [the federal Centers for Medicare and Medicaid Services]. We’ve been working with HealthEC, incorporating all of our Medicaid claims data into their platform. So we are creating endless reports.

Webinar

Can Informatics Drive Clinical Quality Improvements Alongside Operational Improvements in Cancer Care?

Due to the complexity of the disease biology, rapidly increasing treatment options, patient mobility, multi-disciplinary care teams, and high costs of treatment - informatics canplay a more...


Kerda DeHaan

We track utilization, cost, we track on the managed health plan side the capitation payments we pay them versus MLR [medical loss ratio data]; our fraud and abuse team has been making great use of it. They’ve identified $8 million in costs from beneficiaries no longer in the District of Columbia, but who’ve remained on our rolls. And for the reconciliation of our payments, we can use the data warehouse for our payments. Previously, we’d have to get a report from the MMIS [Medicaid management information system] vendor, in order to [match and verify data]. With HealthEC, we’ve got a 3D analytics platform that we’re using, and we’ve saved money in identifying the beneficiaries who should not be on the rolls, and improved the time it takes for us to process payments, and we can now more closely track MCO [managed care organization] payments—the capitation payments.

That involves a very high volume of healthcare payments, correct?

Yes. For every beneficiary, we pay the managed care organizations a certain amount of money every month to handle the care for that beneficiary. We’ve got 190,000 people covered. And the MCOs report to us what the provider payments were, on a monthly basis. Now we can track better what the MCOs are spending to pay the providers. The dashboard makes it much easier to track those payments. It’s improved our overall functioning.

We have over 250,000 between managed care and FFS. Managed care 190,000, FFS, around 60,000. We also manage the Alliance population—that’s another program that the district has for individuals who are legal non-citizen residents.

What are the underlying functional challenges in this area of data management?

Before we’d implemented the data warehouse, we had to rely on our data analysis and research division to run all the reports for us. We’d have to put in a data request and hope for results within a week. This allows anyone in the agency to run their own reports and get access to data. And they’re really backed up: they do both internal and external data reports. And so you could be waiting for a while, especially during the time of the year when we have budget questions; and anything the director might want would be their top priority.

So now, the concern is, having everyone understand what they’re seeing, and looking at the data in the same way, and standardizing what they’re meaning; before, we couldn’t even get access.

Has budget been an issue?

So far, budget has not been an issue; I know the warehouse cost more than originally anticipated; but we haven’t had any constraints so far.

What are the lessons learned so far in going through a process like this?

One big lesson was that, in the beginning, we didn’t really understand the scope of what really needed to happen. So it was underfunded initially just because there wasn’t a clear understanding of how to accomplish this project. So the first lesson would be, to do more analysis upfront, to really understand the requirements. But in a lot of cases, we feel the pressure to move ahead.

Second, you really need strong project management from the outset. There was a time when we didn’t have the appropriate resources applied to this. And, just as when you’re building a house, one thing needs to happen before another, we were trying to do too many things simultaneously at the time.

Ultimately, where is this going for your organization in the next few years?

What we’re hoping is that this would be incorporated into our health information exchange. We have a separate project for that, utilizing the claims data in our warehouse to share it with providers. We’d like to improve on that, so there’s sharing between what’s in the electronic health record, and claims. So there’s an effort to access the EHR [electronic health record] data, especially from the FQHCs [federally qualified health centers] that we work closely with, and expanding out from there. The data warehouse is quite capable of ingesting that information. Some paperwork has to be worked through, to facilitate that. And then, ultimately, helping providers see their own performance. So as we move towards more value-based arrangements—and we already have P4P with some of the MCOs, FQHCs, and nursing homes—they’ll be able to track their own performance, and see what we’re seeing, all in real time. So that’s the long-term goal.

With regard to pulling EHR information from the FQHCs, have there been some process issues involved?

Yes, absolutely. There have been quite a few process issues in general, and sometimes, it comes down to other organizations requiring us to help them procure whatever systems they might need to connect to us, which we’re not against doing, but those things take time. And then there’s the ownership piece: can we trust the data? But for the most part, especially with the FHQCs and some of our sister agencies, we’re getting to the point where everyone sees it as a win-wing, and there’s enough of a consensus in order to move forward.

What might CIOs and CMIOs think about, around all this, especially around the potential for collaboration with government agencies like yours?

Ideally, we’d like for hospitals to partner with us and our managed care organizations in solving some of these issues in healthcare, including the cost of emergency department care, and so on. That would be the biggest thing. Right now, and this is not a secret, a couple of our hospital systems in the District are hoping to hold out for better contracts with our managed care organizations, and 80 percent of our beneficiaries are served by those MCOs. So we’d like to understand that we’re trying to help folks who need care, and not focus so much on the revenues involved. We’re over 96-percent insured now in the District. So there’s probably enough to go around, so we’d love for them to move forward with us collaboratively. And we have to ponder whether we should encourage the development and participation in ACOs, including among our FQHCs. Things have to be seen as helping our beneficiaries.

What does the future of data management for population health and care management, look like to you, in the next several years?

For us in the District, the future is going to be not only a robust warehouse that includes claims information, vital records information, and EHR data, but also, more connectivity with our community partners, and forming more of a robust referral network, so that if one agency sees someone who has a problem, say, with housing, they can immediately send the referral, seamlessly through the system, to get care. We’re looking at it as very inter-connected. You can develop a pretty good snapshot, based on a variety of sources.

The social determinants of health are clearly a big element in all this; and you’re already focused on those, obviously.

Yes, we are very focused on those; we’re just very limited in terms of our access to that data. We’re working with our human services and public health agencies, to improve access. And I should mention a big initiative within the Department of Health Care Finance: we have two health home programs, one for people with serious mental illness issues, the other with chronic conditions. The Department of Behavioral Health manages the first, and the Department of Health Care Finance, my agency, DC Medicaid, manages the second. You have to have three or more chronic conditions in order to qualify.

We have partnerships with 12 providers, in those, mostly FQHCs, a few community providers, and a couple of hospital systems. We’ve been using another module from HealthEC for those programs. We need to get permission to have external users to come in; but at that point, they’d be able to capture a lot of the social determinants as well. We feel we’re a bit closer to the providers, in that sense, since they work closely with the beneficiaries. And we’ve got a technical assistance grant to help them understand how to incorporate this kind of care management into their practice, to move into a value-based planning mode. That’s a big effort. We’re just now developing our performance measures on that, to see how we’ve been doing. It’s been live for about a year. It’s called MyHealth GPS, Guiding Patients to Services. And we’re using the HealthEC Care Manager Module, which we call the Care Coordination Navigation Program; it’s a case management system. Also, we do plan to expand that to incorporate medication therapy management. We have a pharmacist on board who will be using part of that care management module to manage his side of things.

 

 


See more on Population Health

betebet sohbet hattı betebet bahis siteleringsbahis