At St. Louis’s Mercy Health, an Analytics-Driven Performance Push | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

At St. Louis’s Mercy Health, an Analytics-Driven Performance Push

October 3, 2016
by Mark Hagland
| Reprints
Gil Hoffman and Curtis Dudley of Mercy Health share their perspectives on data-driven performance improvement

Major data analytics-fueled clinical and operational performance improvement has been taking place at Mercy Health, the 45-hospital, 300-clinic integrated health system that is based in the St. Louis suburb of Chesterfield, Missouri, and which serves patients and communities in four states—Missouri, Oklahoma, Arkansas, and Kansas.

Leveraging powerful data analytics tools, Mercy leaders have made dramatic progress in a number of clinical areas and services, from the large perioperative area, to cardiology, to laboratory, to pharmacy.

Among those helping to lead an organization-wide charge on operational performance improvement are Gil Hoffman, Mercy Health’s CIO, and Curtis Dudley, its vice president of integrated performance solutions.

Among other things, Hoffman and Dudley collaborated with a large, system-wide team of colleagues to develop a system-wide cost-per-case perioperative dashboard, which provided a wealth of opportunities for the organization’s clinical and administrative leaders to improve performance along a number of dimensions, through monitoring, measuring, and improving costs and clinical outcomes of a variety of surgical procedures. Indeed, using key cost and outcomes data related to surgical procedures across the entire integrated system, Mercy Health achieved $9.42 million through cost reduction, the elimination or minimization of the use of certain surgical products, reduced supply utilization variation, and best practices across perioperative departments in the system.

As Hoffman and Dudley note, Mercy Health has a very high volume of surgical procedures—about 210,000 procedures annually—with the system’s second leading driver of cost coming from surgical supplies and implants. The health system’s leaders looked at that reality and also at the opportunity to impact quality and the patient experience, and went to work, with the system’s perioperative team and technology services team partnering to create a set of custom dashboards launched through an information portal for one-stop access to high level metrics, reports and data exploration tools for immediate answers, faster decisions and more agile process improvements. The interactive dashboards leverage cutting-edge technology to provide a holistic view, consolidating large sets of diverse clinical, operational and financial data into a single platform.

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

Prior to 2012, determining surgical costs at Mercy was an unstructured, manual process.  At the time, surgeon preference cards and product contracts (which contain supply cost) were the only methods available to determine the cost of surgical procedures. Without data as evidence, there were varying opinions as to the best practice, price and product for a given procedure. As a result, there were significant variations in the cost per surgical case across Mercy.  But, through the use of dashboards, along with extensive governance development, clinician and staff training, and the leveraging of health IT (including the extensive leveraging of the HANA platform from the Charlotte-based SAP), the leaders of the initiative were able to make significant progress, with a system-wide cost savings of $9.42 million across perioperative departments for all surgical procedures as calculated through January 2016, after launching the initiative in 2013. Among other elements, Mercy’s median cost per case for total knee surgery dropped from $7,045 with an interquartile range of $1,999 in 2014, to a median cost per case of $5,527 and interquartile range of $901 in 2016. In addition, following dashboard implementation, there has been a significant drop in costs of intraoperative implants and supplies per case related total knee arthroplasty.

Recently, Hoffman and Dudley spoke with Healthcare Informatics Editor-in-Chief Mark Hagland to discuss some of the elements of their organization’s success to date with this system-wide performance initiative. Below are excerpts from that interview.

Tell me a bit about the secret of your success so far with this wide-ranging initiative?

Gil Hoffman: Part of the secret is that our team really focused on how to look at the best outcomes, and then determined what were the best practices involved, and determined how to deliver those good outcomes as efficiently as possible, by reducing costs and improving care.


Gil Hoffman

Curtis Dudley: I’ve been at Mercy health for 27 years. I came from our supply chain division, and have been there for 20 years. I led our Texas warehouse system implementation, the implementation of our Lawson ERP and deployment of that system system-wide, and through that, our supply chain system that we created, which has won a number of awards. A lot of that has been enabled by analytics and data, and that is what brought me to corporate headquarters four years ago. I’ve led our OR operations, supply chain, etc.

And when I came into this role four years ago, I knew we would need data and analytics. So we did a current-state analysis; and what we found in nursing, in lab, in pharmacy, in perioperative, in cardiology, everywhere, was that people were running native reports inside applications, and spending a lot of hours in Excel trying to merge them. So we wanted to unify the delivery experience of analytics, so that people could simply go quickly to analytics and reports. We set out to do this through our business intelligence platform. And, as we prepared to move forward with this initiative, we went to our chief nursing officer, our vice president of laboratory, and to periop, and asked those leaders which metrics drove their business. And because I had knowledge of the periop business and data, and had built a cost-per-case dashboard in Cognos, I went there first. That’s why a lot of our case studies and areas of focus have been in periop.


Curtis Dudley

So we took a service line- and data mart-oriented approach, pulling data from Epic, from Lawson, from an outside data cleansing service, from our outside contractors—and it’s a challenge to pull all those sources of data together. So we spent a lot of time creating a data platform. And we found that there is so much data involved in periop that, to provide an effective data mechanism, we couldn’t show people thousands of lines of raw data. What we needed to do was to roll up those rows of records into dashboards; but traditional means wouldn’t work. We were on Oracle, and Oracle is great, but it just wasn’t robust enough to do this. And we had a long relationship with SAP, partly because of Epic. So we loaded the data in a HANA environment. SAP Business Objects is the suite of tools we leveraged, and SAP HANA is the data platform involved.

So we were able to load all this data, including multiple years of costs per case, and drill down into the individual service or specialty level, or by doctor. But the key thing that’s enabled our success is a variation-oriented approach. So, for example, the dashboard helped us see why one doctor was doing a total knee replacement for $10,000 per case, versus another at $4,000 per case. So using SAP-Hana, we were able to drill down that far. And because the data set was so big, loading into this Hana PLATFORM, I could load these 40 million rows of data, and view it all. Over three years of data in periop, documenting every case, over 210,000 procedures a year, across three full years, that led to the 40 million lines of data.

And because we can real-time-interact with that, we can ask questions, and get to those answers in real time. So I can find out that the reason that this doctor is more expensive than the other doctor is that he’s using specific supplies, for example. So we can work with this and work with the clinicians. And Gil, the HANA investment was pretty extensive, right?

Hoffman: Yes, putting this volume together provided us with these reports, in a reasonable time, when it would have meaningful use.

What are your thoughts on optimizing data use, as a CIO?

Hoffman: I’ve been with Mercy going on five years now, and I came from outside healthcare. And it seemed to me when I got here that healthcare had been sitting on a ton of data for years, but hadn’t been using it to dramatically improve patient care or efficiency. But data really is becoming the tool that gets things done better than they’ve been done before. And using analytics is becoming more and more critical to the success of healthcare. For Mercy, it’s made a dramatic difference in patient care, in the patient experience, in our business work—the ability to get data in real time because of the tools.

Dudley: We saved $9.4 million in cost-per-case reductions this year in periop. That just has periop numbers, but we saved $9 million in cardiology, $1 million in lab, and $2.5 million in pharmacy.

Where did those large doses of savings come from?

Dudley: In cardiology—it’s all come about by taking a variation-oriented approach. One great example involved cardiac stents. It turned out that Mercy had 1.62 stents implanted per patient, versus 1.42 stents per patient, on average nationwide. And when we analyzed that, we found that where we were implanting two stents per patient, there were single stents available that had the same clinical outcomes. So our success in that area required looking not only at costs, but also at quality outcomes, including infection rates, complication rates, etc. So that was an important part of this, improving quality and lowering costs, and improving patient satisfaction.

And where did the $1 million savings come from, in the laboratory area?

Dudley: There was a rapid, expensive cardiac test used in our ER departments, and we switched that out with a test used in the lab that was less expensive; there were a few other similar situations, around unnecessary lab tests or overtesting. We were testing for a heart attack inside the ER many times, when clinical evidence shows that there should be a 2-4-hour gap between giving the heart attack test, otherwise, there’s no benefit.

And the pharmacy savings?

Dudley: In the pharmacy, we have a lot of inventory across our network—we have Omnicell cabinets everywhere, and we were able to analyze the inventory quantities in the cabinets, and found where there was inventory that wasn’t moving, and could shift inventory to where it was needed. So there was a cost element, and also, some medications that weren’t being utilized that were taking space, and also, we could get meds that were needed into those cabinets, so there were patient and nurse satisfaction elements in having certain meds made more available, per reducing medication inventory stored.

What have been the biggest lessons learned so far in all this?

Dudley: There have been so many learnings. A couple I would highlight: the challenge in doing this work. There’s a big technical challenge, involving creating the data platforms. Tools like the HANA platform, and also Hadoop—having a robust, high-performing data platform makes this possible. A lot of times, you underestimate or undervalue how important that is. The second lesson learned is that there’s a journey to be pursued with the business people. Along the way in delivering these metrics, we help them analyze their business in ways that couldn’t be done otherwise. With cardiology, lab, and pharmacy, we were able to help them better understand how their internal operations work. All this time in healthcare, putting in systems and asking clinicians and others to enter data into systems, we hadn’t given them data back in ways that could improve care and efficiency. We’re doing that, and the clinicians are valuing that.

Hoffman: And there’s more to this than just metrics. It takes different types of talent from different people, to bring together those correlations and data points, to take action and make better decisions. There’s just so much to learn from this, to better the patient outcomes and experience. It’s more than just the metrics, more than just measuring certain levels of performance; you’ve got to be able to interpret those pieces of data.

What would you say to CIOs and CMIOs about your experience so far?

Hoffman: Every CIO needs to look at how they can leverage the data they have to improve operations. I’m not sure that everybody has the time and capacity to do this—you have to invest the time it takes to get information out of these systems. So make the investment to get the value out of these systems to be able to learn everything you can learn.

Dudley: And I would just add that there’s really not a choice here. It’s do-or-die time, and it’s incredibly important for organizations to do this. And I don’t know that organizations need to reinvent the wheel. There are numerous collaborative ways to get to this. But you don’t have to reinvent the wheel; there are a lot of people you could partner with to make this happen.


2018 Raleigh Health IT Summit

Renowned leaders in U.S. and North American healthcare gather throughout the year to present important information and share insights at the Healthcare Informatics Health IT Summits.

September 27 - 28, 2018 | Raleigh


/article/analytics/st-louis-s-mercy-health-analytics-driven-performance-push
/news-item/analytics/portal-makes-genomic-clinical-data-resources-available-pediatric-health

Portal Makes Genomic, Clinical Data Resources Available to Pediatric Health Researchers, Families

September 13, 2018
by David Raths, Contributing Editor
| Reprints
Goal is to help accelerate the discovery of precision-based treatments for pediatric disorders

A new data resource portal at the Children’s Hospital of Philadelphia (CHOP) offers researchers, clinicians and families access to open-source and cloud-based data resources to share information about childhood diseases, including pediatric cancer and birth defects.

CHOP’s Gabriella Miller Kids First Data Resource Center (DRC), a collaborative effort supported by the NIH Common Fund launched the data resource portal to help accelerate the discovery of precision-based treatments for pediatric disorders.

Led by CHOP’s Center for Data Driven Discovery in Biomedicine (D3b), DRC partners include the hospital’s Department of Biomedical and Health Informatics, Children’s National Health System, Ontario Institute for Cancer Research, Center for Data Intensive Science at the University of Chicago, Oregon Health and Science University and Seven Bridges, a biomedical data analysis company.

According to CHOP, the Kids First Data Resource Portal provides access to newly released, large-scale NIH-sponsored and consortia-based pediatric genomic and clinical disease data, and empowers accelerated discovery efforts by enabling collaborative cloud-based analyses across institutions and researchers around the globe.

Data from approximately 8,000 DNA and RNA samples from children affected with cancer or structural birth defects and their families will be ready for analysis with the launch of the portal and are expected to grow to more than 30,000 over the next few years. The Kids First Data Resource Portal will be one of the largest collections of integrated genomic and clinical data for these childhood diseases, which previously were studied largely in isolation.

The portal also provides rich resources for the patient, medical and research communities to partner, learn and interact with the Kids First DRC, highlighting the importance of collaboration and data sharing across institutions and between disease communities.

“In a prepared statement, Adam Resnick, Ph.D., lead principal investigator of the Kids First DRC and director of the D3b at CHOP’s Division of Neurosurgery, discussed the significance of the research portal: “The DRC’s Kids First research portal represents a data-driven discovery milestone for the implementation of tools and resources for performing biomedical research and for doing science collaboratively in entirely new and unprecedented ways in the hopes of accelerating discovery and clinical translation for each and every child suffering from cancer or a structural birth defect around the globe,”

Last year Healthcare Informatics published an in-depth interview with Dr. Resnick about the collaborative approach CHOP and other pediatric hospitals are taking to research and biomedical data analysis.

 

 

More From Healthcare Informatics

/article/analytics/putting-social-determinants-health-data-action

Putting Social Determinants of Health Data into Action

September 10, 2018
by Heather Landi, Associate Editor
| Reprints
Healthcare leaders engaged in these efforts have found that health IT is foundational to this work in the collection of social determinants data as well for data exchange across the care continuum and risk stratification
Geisinger's Fresh Food Farmacy initiative

Healthcare providers that provide direct patient care have long recognized that social and economic factors have a significant impact on the health of an individual, and the health of populations, yet it has only been in the past few years that healthcare organizations have started to formalize an approach to addressing social determinants of health, such as food insecurity, housing, transportation and literacy.

These efforts to focus more on the upstream factors that influence patients’ health are occurring in parallel to the healthcare industry’s ongoing transition from fee-for-service to value-based care and payment models, as patient care organizations look to improve health outcomes and reduce costs. For health systems, moving beyond facility walls to collect and incorporate social determinants data into community level programs represents the next phase of population health management strategy.

“Healthcare providers have known for a long time that social determinants are incredibly important, but there hasn’t been, in a regular fee-for-service model, an incentive for healthcare organizations to partner with community-based organizations,” says Robert Fields, M.D., senior vice president and chief medical officer for population health at the New York City-based Mount Sinai Health System. “When you start to get paid on outcomes and reductions in total cost of care then it makes it financially reasonable to invest upstream into infrastructure and preventive care. Many times, that preventive care looks a lot like closing social determinants gaps to avoid the downstream cost. The economics are changing.”

Robert Fields, M.D.

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

Indeed, a report from the Deloitte Center for Health Solutions based on a survey with hospital officials about their efforts to gather and analyze social data about their patients found that there was a high correlation between health systems that were screening for social determinants and those that were involved in at-risk payment models and were already pretty far along in their journey to value-based care.

What’s more, researchers at the University of South Florida (USF) College of Public Health, Tampa, and WellCare Health Plans found that healthcare spending is substantially reduced when people are successfully connected to social services that address social barriers. The researchers’ study, which assessed the impact of social services among 2,700 Medicaid and Medicare Advantage members on healthcare costs, reported an additional 10 percent reduction in healthcare costs—equating to more than $2,400 per person per year savings—for people who were successfully connected to social services compared to a control group of members who were not.

Healthcare leaders engaged in these efforts have found that health IT is foundational to this work in the collection of social determinants data as well for data exchange across the care continuum, workflow integration and analytics to risk stratify the highest-need individuals. Leading hospitals, medical groups, and health systems, as well as accountable care organizations (ACOs) and health insurers are moving forward in this work with a number of different approaches.

Early Efforts to Capture SDoH Data

At Rush University in Chicago, clinical and IT leaders developed a social determinants of health screening tool within the electronic health record (EHR) to combine with clinical registry data. Rush University Medical Center leveraged the NowPow platform and integrated it into the workflows of the primary care physicians and frontline staff, according to Michael Hanak, M.D., associate chief medical informatics officer at Rush University.

After the provider completes the patient intake process, the Rush EHR combines the social data with the medical history into a patient profile that it sends to NowPow. The software queries the company’s database of local community resources to identify where patients can receive needed services. NowPow then provides a curated list of resources and services — called a HealtheRx—that matches the patient’s needs. The technology enters the HealtheRx in the patient’s medical record, sends it to the identified community-based providers, and emails and/or texts it to the patient.

Michael Hanak, M.D.

“This is a gamechanger for population health,” Hanak says. Clinical IT leaders are collecting the social data and using that to risk stratify patients. “That’s helpful when we look at our patients who are in managed care contracts, so we’re applying wraparound services to our higher-risk patients and the social determinants screening is part of that.”

Hanak says patient navigators used the tool to screen patients who were no-shows for doctor’s appointments. “We found that nearly one-third of these patients who had missed a visit had a social need that we could assist with. Our hope is that we see that actually improves adherence to visits and engagement with care,” he says.

Clinicians at the University of Arkansas Medical Sciences (UAMS) Medical Center in Little Rock are prompted by their EHR to ask patients questions about their personal life regarding their financial situation, drinking habits, social isolation and domestic abuse as part of the hospital’s efforts to standardize the collection of social needs data. Stephen Mette, M.D., the medical center’s chief clinical officer, says clinical and IT leaders began an effort about two years ago to embed these questions in the EHR as part of a larger mission at UAMS to systematically address social health inequities that create health disparities.

Stephen Mette, M.D.

“Technology is wonderful in that it allows us to have ready access to data, and the ability to analyze the data and package the data in useful ways to allow the data to be used to inform clinical decisions by providers,” he says, although he adds that the accuracy of data and the availability of data to providers continue to be challenges. “But, we’re much further ahead than we were a few years ago because of our data systems.”

Bradley Hunter, research director at Orem, Utah-based KLAS Research, says health information exchanges (HIEs) are well-positioned to play a vital role in these efforts by bridging gaps between the healthcare and social services sectors. In fact, the Strategic Health Information Exchange Collaborative (SHIEC) recently established a Social Determinants Committee, with the core aim to help SHIEC better focus on identifying and linking social determinants of health data and to overcome challenges for data exchange between health and social service entities.

Leveraging SDoH Data for Population Health Efforts

Health insurer Humana is actively addressing social determinants of health as part of its Bold Goal initiative, with a goal of improving the health of the communities it serves 20 percent by 2020. Measuring progress using the U.S. Centers for Disease Control and Prevention (CDC) population health management tool known as Healthy Days, Humana found that implementing community-level changes has led to positive health outcomes for elderly beneficiaries with heart disease, diabetes, respiratory conditions and other chronic diseases. For example, individuals in Humana’s San Antonio Bold Goal community saw a 3.5 percent improvement in Healthy Days and Knoxville participants saw a 5.4 percent improvement.

Many integrated health systems such as Kaiser, Partners, Intermountain and Geisinger also are at the forefront of these efforts.

As a participant in the MassHealth (Medicaid) ACO, Boston-based Partners Healthcare is required to screen Medicaid ACO patients for social determinants factors and has integrated that process into its primary care practices.

“It’s not just screening for screening’s sake,” says Rose Kakoza, M.D., assistant medical director for Medicaid for the Center of Population Health at Partners Healthcare. “We’ve been very thoughtful to think about, as we screen for social determinants of health, we need to make sure we have the appropriate resources in place to manage the needs that come to light as a result of that screening.” To address this, the organization deployed parallel care management strategies and increased its staff of community resource specialists and social work support.

Partners also worked with its eCare team (eCare is the organization’s enterprise-wide Epic EHR) to map the positive screening results to ICD-10 codes, enabling clinical leaders, for the first time, to track unmet social needs in a systematic way. The next phase, Kakoza says, is to integrate a platform into the EHR to track whether the referral loop was closed.

Danville, Pa.-based Geisinger Health System also is further along on this path with an innovative initiative, called Fresh Food Farmacy, that aims to address food insecurity, as a significant social factor impacting health, and to improve patients’ diabetes management. Geisinger’s Fresh Food Farmacy provides fresh, healthy food to diabetes patients, at no cost to the patients. The health system initially launched the program in July 2016 as a pilot project at Geisinger Shamokin Area Community Hospital in Coal Township, in Northumberland County, which has the second-highest rate of long-term diabetes complications in central Pennsylvania.

Project leaders have seen significant improvements in clinical outcomes for patients enrolled in the Food Farmacy program, to date. Robust data analytics plays a critical role in the success of the project, says Andrea Feinberg, M.D., medical director of Health and Wellness at Geisinger Health and the clinical champion of the initiative. “The data analytics is huge; we have an incredible dashboard that we use and it tracks what’s going on with the patients and the program. Without that, we would not be able to support the work that we’re doing,” she says.

At New York City-based Mount Sinai Health System, leaders of the organization’s ACO, Mount Sinai Health Partners, are working with Lumeris, a St. Louis-based health plan and managed services vendor, to use its analytics platform to identify the social needs of its 400,000 members, connect them to community resources and then risk stratify patients for further intervention. IT leaders also are working to integrate the social determinants care plan and the workflows into its health IT systems.

According to Fields, Lumeris’ platform leverages publicly available data, such as census data, and also purchases social determinants data, like credit agency data, and then combines that with claims data, and the runs the data through artificial intelligence (AI) and machine learning to come up with predictive modeling for patients at risk of hospital admission. Fields led similar successful efforts at Asheville, North Carolina-based Mission Health Partners, what he calls a “heavily social determinants-driven” Medicare ACO affiliated with the Mission Health healthcare system.

“With this predictive modeling, I can tell you with a relatively high degree of certainty, for any of our attributed lives, the risk of a patient ending up in the hospital for an unplanned admission within the next 30 days, which is amazing, to think about, being able to look upstream,” he says. “As a provider or a care management entity, if you knew that a specific patient was going to end up in the hospital, what would you do differently? Probably a lot. That’s what we started to work with at Mission, and now we’ll be working here at Mount Sinai, using that predictive model to start prioritizing patients to figure out who might need outreach and what kind of outreach that might be.”

He also notes that analytics, and specifically predictive analytics, are critical components to this work. “Any ACO or any participant in value-based care has a set amount of resources, they are not unlimited.
What analytics allows you to do is really identify those patients that are likely to have a bad outcome or lead to high cost, ideally before that happens, and then, of those patients that are likely to have a bad outcome, who is likely to benefit from what specific social determinant need. To the degree that analytics and predictive analytics can start to identify those for you, it saves hours of potential evaluation and assessment of the patients in your population. And the efficiency that will come from that is pretty unbelievable,” he says, adding, “Both predictive analytics and risk stratification are incredibly important to be able to identify and then prioritize the patients.”

Challenges to Addressing SDoH

The Deloitte Center for Health Solutions study on social determinants of health within healthcare systems found that there is strong interest, but lack of funding and little measurement of impact.

According to the report, 80 percent of the people surveyed said, yes, social needs are a core part of our mission. Seventy-two percent said they don’t have sustainable funding to do it. In an interview with Healthcare Informatics Contributing Editor David Raths about the report, Josh Lee, a principal in the firm’s Healthcare Provider Strategy Practice, said, “That is in many ways a heartbreaking mismatch. They are saying ‘we know this should be part of our mission, but we really don’t know how we can pay for it.’ Forty percent felt they were doing something in this regard, but had no way of measuring whether it was working or not. Those three numbers—80, 72 and 40—tell the story.”

Mount Sinai’s Fields also notes that operationalizing this work continues to be very challenging as addressing social needs is still based on having a relationship with the patient. “Even with all the technology in the world, it’s still challenging to develop operations that can actually make an impact and engage with patients in this work. It requires a great deal of sensitivity and whole lot of patience to engage with patients in this work.”


Related Insights For: Analytics

/article/analytics/emerging-world-risk-based-contracting-data-analytics-foundational-necessity

In the Emerging World of Risk-Based Contracting, Data Analytics Is a Foundational Necessity

September 7, 2018
by Mark Hagland, Editor-in-Chief
| Reprints
As patient care organizations engage in more rigorous and challenging risk-based contracts, the need to leverage data and analytics to support value-based care delivery operations is becoming paramount

Industry sages have been predicting for years now the time when all the processes around the leveraging of data analytics would become fundamental to operational and financial success among the leaders of U.S. patient care organizations. Well, with the emergence of more and more risk-based contracting, including two-sided risk, that moment has clearly arrived.

Indeed, the August 9 announcement on the part of Seema Verma, Administrator of the federal Centers for Medicare and Medicaid Services (CMS), of a proposal dubbed “Pathways For Success,” appeared to mark an inflection point in the U.S. healthcare system’s journey around risk-based contracting. That proposal, if finalized, would remove the traditional three tracks in the voluntary Medicare Shared Savings Program (MSSP), and replace them with two tracks that eligible ACOs would enter into for an agreement period of no less than five years: the BASIC track, which would allow eligible ACOs to begin under a one-sided model and incrementally phase in higher levels of risk; and the ENHANCED track, which is based on the program’s existing Track 3, providing additional tools and flexibility for ACOs that take on the highest level of risk and potential rewards. That proposal has received very mixed reviews among patient care organization and ACO leaders, with some ACO leaders pushing back on CMS, asserting that two-sided risk is still too difficult and challenging for many provider organizations.

But regardless of the near-term and middle-term fate of “Pathways For Success,” industry leaders fully recognize that the U.S. healthcare system is inevitably headed further into risk-based contracting, including into two-sided risk-based contracting—however long it might take to reach a tipping point, in which the majority of patient care organizations are receiving significant percentages of their reimbursement via two-sided risk.

A Lot of Basic Blocking-and-Tackling Obstacles Remain

Webinar

Experience New Records for Speed & Scale: High Performance Genomics & Imaging

Through real use cases and live demo, Frank Lee, PhD, Global Industry Leader for Healthcare & Life Sciences, will illustrate the architecture and solution for high performance data and AI...

Of course, the urgency on the part of the purchasers and payers of healthcare to push providers into two-sided risk makes absolute economic sense, says Don Crane, president and CEO of America’s Physician Groups (APG), a Los Angeles-based, nationwide association of physician groups involved in risk-based contracts. “Upside risk makes sense for a while, baby steps,” Crane says. “But it’s weak tea in terms of driving real change. If you get lucky with the right benchmarks, you can do well. But it doesn’t induce real structural change. But when an organization faces downside risk, also known as bankruptcy—that really forces change. When you take that higher risk, you have to have the data. You have to risk-stratify your population, and treble down on the resources you’re using on the patients at highest risk.” And, he adds, “All of a sudden, you move into the big leagues.”

Don Crane

Still, despite the fact that the purchasers and payers of healthcare are pushing providers forward to take on more risk and downside risk in their contracts, the leaders of patient care organizations remain challenged by many rather basic blocking-and-tackling types of data management and analysis challenges. As Liam Bouchier, principal advisor at the Naperville, Ill.-based Impact Advisors consulting firm, puts it, “The data challenge is not a new challenge; the biggest challenge is still getting a complete and comprehensive view of the patient. It’s only been in the past five years that information has really begun to flow. When you look at a longitudinal view of the patient’s care, it’s important to see what’s happened between hospital stays,” he adds.

Fred Horton, president of AMGA Consulting, the consulting arm of the Alexandria, Va.-based American Medical Group Association (AMGA), a nationwide association of large medical groups, says that “There are a couple of different areas” of fundamental concern, as provider organizations move to leverage data analytics in order to manage risk. “Number one is the investment in the EHR [electronic health record]. A lot of health systems are roll-ups of multiple organizations, so you may have multiple EHRs to gather data from. There are EHR-agnostic tools that can analyze data coming from multiple EHRs. That trend will continue into the future. But then there’s the piece involving how much a particular patient is seen by a particular health system, and that’s a challenge. Let’s say some of the urgent care visits and some of the primary care visits are happening outside your health system. How do you ultimately obtain all the data, so you can analyze what’s going on?”

What’s more, he notes, the amount of relevant data in any organization’s EHR “could be less than 25 percent of all the data would be necessary to understand what the potential for risk is. The EHR might capture two or three medical visits a year, but that might actually be a minor element in what you need to truly manage under a risk-based or value-based environment.”

Towards “Generation 2.0” with Data: Predicting First Hospitalizations

The good news in all this is that the leaders of some of the most advanced multispecialty physician groups have steadily been learning how to leverage data, says John Cuddeback, M.D., Ph.D., chief medical informatics officer at AMGA Analytics, the analytics-focused division of AMGA. What have they learned? “I think the fundamental strategy for managing population health depends on risk stratification and matching what you’re doing for each individual person within the population, with their needs. And if you can use data to figure out where they fall on the risk continuum and proactively address primary prevention, secondary prevention, or monitoring of chronic conditions needs, that’s the big opportunity,” Cuddeback says. “And in the very first generation of population health involved clinical decision support in the EHR,” medical group leaders gathered together data on the diseases of their patients with chronic illnesses, and used clinical guidelines to manage their care.

John Cuddeback, M.D., Ph.D.

“The next thing,” Cuddeback says, “was registries, finding the patients who are not coming in, and need a screening or preventive service or something, that’s something like Generation 1.1. Generation 2.0 is using longitudinal data on populations to create predictive models. We know what’s going on for a patient at a particular time, and we know what will probably be going on in two or more years. So let’s take advantage of that and create good predictive models. We need to find the rising-risk patients and address their needs.”

Very importantly, Cuddeback says, “One of the big advantages of having clinical data is that you can predict an initial hospitalization. Historically, people have used claims data well to build predictive models. But the weakness with claims data is that you’re building models based on historical data, meaning you’re looking towards potential readmissions. So predicting initial admissions is the new thing that people are working on. But the implementational aspect of this is that you have to become much more proactive in your care design. Because if you’re just waiting for people to arrive, the predictive model does you no good. So the predictive model will help you figure out who your rising risk populations are. But we have to change our care delivery and management models.”

Moving Forward in Massachusetts: MACIPA’s Path

The senior executives of physician groups who have been working in the trenches in value-based healthcare delivery and payment are working through a series of challenges. One medical group that exemplifies intensive effort in the face of those challenges is the Mt. Auburn Cambridge Independent Practice Association, or MACIPA, a Boston-area, 500-physician independent practice association that participated in the Pioneer ACO Program for three years from 2012 through 2014, and is now in the Track 3 section of the MSSP program. MACIPA president and CEO Barbara Spivak, M.D., a primary care physician, says flatly, “I don’t think you can do risk-based contracting without data. I’m not even talking about the business side; on the clinical side, you need to know who your sick patients are, and we all know that costs go up when there are gaps in care. So you need to know who your sick patients are, where they’re going, and where the gaps in care are. And that’s even before quality management.”

What’s more, Spivak says, “The physicians need actionable data. It doesn’t help me that my colon cancer screening rate is 50 percent and needs to be 60 percent; as a PCP, I need to have the patients identified and to bring them in. The issue is not what we need; what we need is similar to what we needed when we started with electronic records and population health 15 years ago. The challenge is that the data is exponentially more.”

Barbara Spivak, M.D.

Spivak says that she and her colleagues have had no regrets whatsoever about participating in the Medicare ACO programs, despite the frustrations—including that, as of mid-summer of this year, they still had not received key performance data from CMS on their 2017 performance, for example. Indeed, she says, the reality of the complexity of the MIPS (Merit-based Incentive Performance System) program that now governs physician payment under Medicare for those physicians in practice not involved in ACOs and other authorized alternative payment models, is forcing physicians forward. “I believe the way they’ve structured MIPS and MACRA [the overarching law, the Medicare Access and CHIP Reauthorization Act of 2015] is way too complicated for anybody but someone who’s in a big system, where the system’s going to take care of it. If you’re in a small private practice on your own, it’s going to be virtually impossible. It is probably succeeding in pushing people into alternative payment models.”

Moving into Social Determinants Data Management

For years, it’s been a truism that one of the key challenges in harnessing data to support value-based healthcare delivery, has been that of marrying clinical and claims data—a challenge that continues to vex many, if not most, patient care organizations moving into risk. At the same time, one of the important frontier areas emerging around the leveraging of data analytics for value-based healthcare, is the pursuit of data around the social determinants of health. All those who are moving into that area agree that it remains challenging. As MACIPA’s Spivak says, “The EHRs are not always set up to help you with the social determinants. And we are trying to do some of that. I’ll give an example,” she offers. “We have social workers and health coaches. We don’t have a lot, because we’re small. But last year, they identified all the patients 90 and over in our senior products, and called them to make sure that they were being taken care of medically, and had transportation, weren’t living on the second floor and isolated, so we tried to reach out to them.”

Meanwhile, Spivak continues, “This year, we looked at whether they could identify family members—in patients who had dementia, we tried reaching out to those family members of patients. We were not doing it based on people’s insurance, we were doing it based on other factors. So we’ve been trying to do that”—gather and use more social determinants data. “Our care managers of course look at people who are in the hospital two or three times or use the EDs more.”

Of course, it really helps to be working in a payer-provider environment. That’s what the folks at the UPMC health system are doing in western Pennsylvania. The umbrella UPMC organization includes the UPMC Health Plan, and the health plan and provider divisions of the umbrella organization have been collaborating around data for years, in order to improve the health status of covered populations.

Pamela Peele, Ph.D., chief analytics officer at UPMC Insurance Services and UPMC Enterprises, says, “We absolutely have a great advantage in being an integrated health system. You can’t manage what you can’t measure. And providers can only see the patients in front of them. Payers, we get everything. We’re asking providers to manage risks they can’t even see. So we’re trying to give providers a broad view of the risks they’re trying to manage.”

Pamela Peele, Ph.D.

Peele notes that the UPMC Insurance Services and UPMC health system professionals are working forward in a few distinct areas right now. “The first one,” she says, “is around opioid abuse. In conjunction with providers, we’ve been identifying worrisome prescriptions that are ordered in EDs, etc., and we’ve been giving them the data and are identifying those worrisome situations, and are pushing that information right into the EHR so the provider can see it at the point of care. That,” she said, “is a great example of how a payer and provider can come together for the benefit of our membership. And per readmissions, the provider can only see readmission rates in their own facilities. We can see all readmissions via our claims, and can provide information to our providers about true readmission rates.”

And the results? “We’ve definitely seen a decrease in opioid prescribing; and our providers love the collaboration,” Peele reports. “We’ve also seen a decrease in readmission rates over time. If you’re asking a provider to take risk on readmissions, you have to give them accurate data,” she adds. “So when a payer and provider come together, you can accomplish that. And once again, you can’t change what you can’t measure."

And in doing so, Peele and her colleagues are using “very advanced techniques in machine learning,” she says, though she adds, “I don’t like the term ‘artificial intelligence.’” But, she notes, one exciting proect has been the use of a data model that “we’ve built with natural language processing and trained on our clinical care notes. It assigns the probability that somebody is homeless or has housing insecurity. And that’s incredibly important,” she notes. "If you’re homeless, how are you refrigerating your insulin?”

Meanwhile, “We’re still in the early stages of physicians and physician groups moving into social determinants of health data work,” APG’s Crane says. “If you talk to a fee-for-service doctor about social determinants of health, he’ll say, ‘Nice idea, but are you kidding? I didn’t go into healthcare to be a social worker.’ If you talk to APG members, though, you’ll see that they totally understand it.” Indeed, he says, more advanced medical groups, those taking on more risk, are trying to work forward, even as their leaders come quickly to see the challenges of connecting the data side of the SDoH phenomenon with the process side. “You so often need to get into the home, and into transportation, and nutritional support,” in order to make meaningful use of any data gathered for such purposes, Crane says. “If the patients can’t get to the doctor’s office, and aren’t eating and are living in a high-crime area, no amount of good diagnosis and prescription will produce a good outcome.”

Things are moving forward on multiple fronts, Crane notes. “In Medicare Advantage, given the latest rate note and the bipartisan Balanced Budget Act, Medicare is basically beginning to cover social determinants of health stuff; that’s in a nascent stage, but people are gearing up for it,” he says. “I think I saw that Humana and Ascension Health have created a new venture around social determinants. And we’ve entered into a partnership with Partners in Care, a foundation headquartered in Los Angeles. They’re available for hire to do home visits and other similar sorts of social work items. And my members are hiring them to do that kind of outreach into patient’s homes. It’s really helpful with the frail elderly and such. So seeing where the puck is headed there, we entered into a partnership with Partners in Care. And that’s a whole new frontier.”

Advice for Health I.T. Leaders

As the leaders of patient care organizations move their organizations further into risk-based contracts, inevitably, those interviewed for this article agree, the data analytics processes to support value-based care delivery will become more sophisticated, nuanced—and successful. In the meantime, what should the CIOs, CMIOs, and other healthcare IT leaders of patient care organizations, be thinking and doing, in this important area?

“Figuring out how to improve predictive modeling is one thing, and that means getting additional information that has predictive value,” says the AMGA’s Cuddeback. “And, in that context, everyone is recognizing that gathering social determinants of health information is important. For example, Lehigh Valley Health Network is actually working at the level of the census block group. Most of the socioeconomic measures are available from the Census Bureau at the census block group level, roughly 1,500 people. So if you actually know the resident’s address and are able to map it at that level—then you’re able to get the census data for that group of about 1,500 people,” for example. That granular level of data collection and analysis, he says, will be one key to moving forward successfully in the rapidly evolving world of risk-based contracting, he says.

Meanwhile, speaking of the foundational importance of data analytics to the entire value-based healthcare operations venture, APG’s Crane says bluntly, “There’s no future around fee-for-service; it’s eroding out from under doctors,” says Crane, whose association represents more than 300 physician groups operating in 45 states, the District of Columbia, and Puerto Rico. “You look at the Medicare fee schedule and increases slated for the future,” he says. “What are they? The anticipated increases to physician payment under Medicare are going to be 0.5 percent, 0.25 percent, from here out to as far as the eye can see, they’ll be nearly flat; and the increases in costs of running practices will be increasing 2, 3, 4, 5, 6 percent. So you’re quickly on the way to the poorhouse if you’re trying to stay in a fee-for-service world. So how will we make a living? To make a living doing what you want to do, you’re going to need to find a different way to make a profit under flat revenue. How do you do that? You keep the population healthier. You stare into the data and figure out who will get sick next, by using predictive analytics.”


See more on Analytics