At The Iowa Clinic, an Analytics-Driven Adult Immunization Project Drives Results | Healthcare Informatics Magazine | Health IT | Information Technology Skip to content Skip to navigation

At The Iowa Clinic, an Analytics-Driven Adult Immunization Project Drives Results

October 18, 2017
by Heather Landi
| Reprints
As a result of the project, The Iowa Clinic increased the pneumococcal vaccine rate in the 65 and older group to 77 percent, a 21 percent increase
Click To View Gallery

As patient care organizations across the country delve into population health work, physician leaders are finding that data-driven projects aimed at improving adult immunization rates can be an effective area to target to improve the health of patient populations, while also producing significant clinical quality improvements.

Every year, an estimated 1 million older adults contract pneumococcal pneumonia and five to seven percent will die, according to data from the AMGA Foundation, the research arm of the Alexandria, Va.-based American Medical Group Association (AMGA). Further, pneumococcal disease accounts for $3.5 billion in direct medical costs, and pneumococcal disease in patients 65 and older accounts for the majority of the $3.5 billion, the most severe cases, and nearly 2 million hospital days each year.

To address gaps in its adult vaccination rates, The Iowa Clinic, a West Des Moines-based multispecialty practice serving central Iowa, initiated an analytics-driven collaborative project to increase immunization rates in adult patients, with a specific focus on pneumococcal pneumonia and influenza immunizations. The Iowa Clinic is the largest physician owned multi-specialty group in central Iowa, with more than 200 healthcare providers practicing in 40 specialties. The medical group serves a population area of 1.1 million people, averaging 400,000 patient visits each year.

“We understand, clinically, the cost economics of healthcare, with an ounce of prevention worth many pounds of cure, and when patients receive vaccinations, it greatly reduces the chances of those patients getting influenza or pneumococcal, which can be life-threatening and can result in costly hospitalizations,” Christi Taylor, M.D., chief quality officer, internal medicine at The Iowa Clinic, says.

The Iowa Clinic’s initiative to target adult immunizations was part of the AMGA’s Adult Immunization (AI) Best Practices Learning Collaborative, a 14-month, shared-learning collaborative facilitated by the AMGA Foundation. The pilot involved seven care provider groups working to identify optimal and efficient ways to improve adult immunizations and leveraging the Optum One population analytics platform to support the initiatives.

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...

Data from Optum One indicates that, prior to the collaborative, the median pneumococcal pneumonia vaccination rates across all the participants in the pilot program was 60 percent for adults 65 years old and older, and 16 percent for high-risk adults ages 18 to 65. This is well below the Healthy People 2020 goals, which are 90 percent for adults aged 65 years and older and 60 percent for high-risk adults. The Healthy People 2020 goal for influenza vaccination is 90 percent for both populations.

Across the country, adult immunizations rates are considerably lower than childhood rates. “People are used to giving vaccines to children, particularly with pediatrics and family medicine, but adult vaccines often don’t receive the same attention,” Taylor says. “It’s not that you don’t care as an organization, but when people come in with 15 different things that you need to go through, it’s easy for [immunizations] to be pretty far down on the list.” Taylor also notes that with pediatric and young adult patients there are certain milestones, starting school or going to college, that serve as hard-stop reminders of particular vaccinations, yet there are no such milestones with adult patients. “From a physician’s standpoint, adult vaccines are something that you medically understand that it’s important, but you may be missing at a routine visit,” she says.

A key step in this initiative was establishing an AI team at The Iowa Clinic, which included Taylor, the chief medical officer, the direct of care management and quality, a care manager and physicians from internal medicine, family medicine, cardiology, OB/GYN and pulmonology. The team then designed and implemented strategies to identify and address gaps in recommended vaccination practices using intervention tools that target care providers and patients. Another key step was combining data and analytics with population health management techniques. The Iowa Clinic has a business relationship with Optum Analytics and uses an Allscripts electronic health record (EHR) system, and members of the AI team utilized those tools to gather the relevant data.

One critical component to the success of the project was leveraging objective evidence and ongoing reporting to motivate staff throughout the collaborative, according to Andrea Sorensen, clinical analytics director at The Iowa Clinic. “Going after the doctors and saying, ‘We are part of this collaborative and you need to do a good job with this,’ wasn’t enough. We had to put numbers in front of them to show them how they are doing,” Sorensen says. “And, we are very transparent in how we do that, so if there is a doctor who is lagging, it’s transparent, and nobody wants to be a C student, everybody wants to be on top. So that transparency helped drive the success of the program. We produced weekly and monthly reports for the physicians, their staff and care managers to make sure that everybody who could potentially touch that patient that was missing an immunization was aware of what was going on and had the data sitting in front of them.”

Taylor agrees, adding, “The frequent reporting and having up-to-date results were very helpful, particular for nursing staff. We were able to have weekly huddles and show them their progress, and their vaccination rates from the immediate week prior. If someone’s vaccination rates really plummeted one week, we were able to get on top of that within days and say ‘What’s going on? Why are we falling down on this?’ You could use that frequent feedback to direct behavior change and as part of education for the physicians and staff.”

According to data provided by AMGA’s AI collaborative, prior to the intervention, 55 percent of The Iowa Clinic’s patients age 65 and older had received at least one pneumococcal pneumonia vaccination, while 11 percent of the high-risk patients age 19 to 64 had received at least one vaccination. In the 14-month period that the Iowa Clinic participated in the collaborative, the organization saw its pneumococcal vaccination rates among the 65 and older patient population increase 21 percent, achieving a 77 percent immunization rate. Among high-risk adult patients in the 19 to 64-year-old population, The Iowa Clinic increased the pneumococcal vaccine rate to 22 percent, a 10.8-percent increase. Influenza immunization rates increased by 15 percent to an overall rate of 49 percent.

Increasing the immunization rate among the high-risk, under 65 population continues to be an area of focus, Taylor says. “That’s a population that is the least likely to be vaccinated, because they are younger. There are commercials telling people 65 and older to get their vaccine. It’s easy in a younger population to, frankly, just overlook it, and so, as much as they greatly need it, they might be the least likely to actually receive it,” she says.

The Iowa Clinic

In addition to the ongoing reporting, Taylor says the organization also utilized a dashboard tool embedded in its Allscripts EHR to provide visual reminders to providers and clinical staff. “That is helpful at the point of service when the patient is seeing the provider as either the doctor, nurse practitioner or nursing staff can open up the dashboard and just see, at a quick glance, if that patient is due for a vaccine. It’s very easy in a busy clinical day just to focus on addressing the eight other things that the patient came in for, so the visual reminder that the patient is due for a vaccine was very useful.”

Sorensen says the behavior changes among physicians and clinical staff have been sustainable, due in large part to the ongoing metrics reporting and workflow changes, and providers are continuing to focus on this population health work. Additionally, The Iowa Clinic will be reporting these measures to the Centers for Medicare & Medicaid Services’ (CMS) Quality Payment Program (QPP) under the Merit-Based Incentive Payment System (MIPS), as part of the Medicare Access and CHIP Reauthorization Act of 2015 (MACRA). “When you look all the different measures and metrics that are available as part of the [MIPS] program, the flu shots are also measures in that program, so it makes sense since we were so successful with the 65+ population as part of this collaboration, it was one of those measures that we’re doing well on, so we’re going to continue to focus on it as part of MIPS and MACRA measures,” she says, adding, “So, all our hard work will continue because it needs to be a normal part of business.”

Taylor says there were a number of important lessons learned during the 14-month collaborative project. “One of the steep learning curves for our clinical staff and providers was, inherently, the limitations of population health, in that, when you do massive outreach to hundreds of thousands of people at once, while it’s efficient, it’s not going to be razor specific,” she says. To that point, the practice utilized an automated outreach tool contact patients by telephone who had been identified as needing an updated vaccination and those patients received automated notification messages.

The challenge with that kind of large, automated outreach, Taylor says, is that there can be errors with the wrong patients receiving notifications that do not need to be notified. “With this kind of large outreach, as part of population health management, you need to accept that it isn’t perfect. In retrospect, we should have educated the physicians about that part of the process, that while 99.9 percent of the patients who are contacted will be the right ones, there’s going to be 100 people who will receive notifications who didn’t need to and they called the doctor’s offices and the doctors don’t know why they called. So we need to communicate with patients and doctors about the outreach and what it’s based on,” she says.

According to AMGA, the AI Best Practices Learning Collaborative, which was supported by Pfizer, significantly improved adult vaccination rates for all seven organizations in a little over one year, as measured against a group of similar providers. One focus of the overall collaborative centered on the new CDC guidelines for pneumococcal vaccines in patients age 65 and older. After 14 months, immunization rates in patients aged 65 and older increased from 4 percent to 34 percent. This absolute increase of 30 percentage points compares to an increase of 21 percentage points for a matched cohort of care providers in other organizations that are focused on population health but did not participate in the collaborative, according to AMGA. Based on the success of this collaborative, AMGA Foundation plans to launch an expanded collaborative this year that will involve up to 40 care organizations.


2019 Southern California San Diego 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.

April 23 - 24, 2019 | Southern California


/article/analytics/iowa-clinic-analytics-driven-adult-immunization-project-drives-results
/article/analytics/big-data-new-moneyball

Is Big Data the New Moneyball?

November 14, 2018
by Pamela Dixon, Industry Voice
| Reprints
The new healthcare chief data officer can provide your playbook and data strategy

Anyone who has seen the movie Moneyball, a movie about baseball, will remember the opening scene— old guys talking around a smoky table with marked-up stacks of paper outlining the pluses and minuses of draft prospects. The old guys “critique” these prospects with the knowhow of hard-earned experience, and they talk with the familiarity of a weekly poker match.  

So when they are presented with a buttoned-up computer kid from Yale who will present his draft picks to them, there is a moment of surprised silence.  The kid clicks off his list of little known players to stares of disbelief, and he explains matter-of-factly, “The picks are based solely on statistical analysis.”  That’s when you see their world get upended.

Healthcare may be caught in a similar moment, on the edge of a fundamental shift.  In Moneyball, the shift from money driving decisions to information driving the decisions upended the World Series and, subsequently, the game of baseball.  Big data may similarly upend healthcare.

Admittedly, our opening scene in healthcare has some old guys in the room—half of doctors in the U.S. are over 50 years old—and, yes, they show resistance to change.  Meanwhile, healthcare consumers are in the bleachers increasing pressure for a big win.  And coming on to the playing field is big tech, betting on its AI prowess and other technology tools to address big data. Can it fix healthcare?

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...

Source: CB Insights

Big Tech’s Growing Interest in Healthcare

Following the money, we see big tech’s interest in healthcare starting to grow in 2012 (see above). In 2012, the top-10 tech companies that were involved in healthcare equity deals were worth about $277 million. In 2017, that grew to $2.7 billion. Driving part of the interest is big data.

“It’s not the data,” said Dr. Eric Topol, director of the Scripps Translational Science Institute. “It’s the analytics. Up until three-to-five years ago, all that data was just sitting there. Now it’s being analyzed and interpreted.  It’s the most radical change happening in healthcare.”

What’s in it for Big Tech?

Data-rich Facebook and Google make their money on advertising—an industry worth $200 billion, which is small compared to healthcare’s $3 trillion industry.  David Friend, managing director at account firm BDO, estimates a major opportunity for these two tech giants. “In theory, if this is done right, you’ll have 15 Facebooks and 15 Googles. That’s what’s up for grabs.”

While driving a profit is one opportunity, the ability to capitalize on data is key to developing consumer-centric models of care, improving patient outcomes, and lowering costs—which are all critical for healthcare.  Healthcare systems are working to accomplish the same goals using big data analytics, sometimes together with big tech companies.  A few examples:

  •          Stanford University School of Medicine, in conjunction with Apple’s new app, Apple ResearchKit, enrolled more than 11,000 patients—in 24 hours—which is more than most medical studies achieve in a year, and they collected much more data in 24 hours than they could have otherwise. This was an “eye opener” for them.
  •         The Centers for Medicare and Medicaid Services (CMS) was able to prevent a $210.7 million in fraud in just one year using big data analytics. 
  •          Allina Health System, an integrated delivery system of 13 hospitals and 82 clinics in Minnesota, realized more than $45 million in performance improvement savings over the past five years in a project targeting only cardiovascular care across the system.

So back to our opening scene, we have the old guys in the room resistant to change.  We have the consumers demanding change from the bleachers.  We have big tech on the playing field applying tools to big data to create some wins.  We have a few healthcare providers coming on to the field using data to create wins. But who is our buttoned-up computer kid, the one that puts together the “moneyball” playbook?  Enter the chief data officer; he or she is there to provide your playbook and your data strategy.

The CDO role is generally tasked with oversight of a comprehensive data strategy, enabling a data-driven culture, creating operational efficiencies and, in some organizations, revenue opportunities. These leaders provide the organization with a clear set of objectives and goals.

The chief data officer enters the scene when healthcare is on the threshold of a major shift. In addition to transforming care, controlling costs and enhancing revenue, data can be used to negotiate competitive rates with insurers, set more accurate (and justifiable) prices for healthcare procedures, and create the transparency that consumers are demanding. Understanding the flow of data will also find hidden opportunities to control costs and enhance revenue. Just your basic “moneyball” playbook.

While the CDO role has gained broad acceptance outside of healthcare, adoption has been very slow inside healthcare.  According to the International Institute for Analytics, which ranked various industries’ ability to harness data, healthcare providers came in last—lagging behind all other industries and all other healthcare segments, including health insurers.

"Moneyball" helped level the playing field by looking at information. This is where healthcare providers also start playing the game with new tools and a new type of leader.

Pamela Dixon, managing partner

www.castlightsearch.com

404-479-4990


More From Healthcare Informatics

/article/analytics/olympic-marathons-performance-improvement-initiatives-help-power-long-race

Olympic Marathons: Performance Improvement Initiatives Help to Power the Long Race

November 14, 2018
by Mark Hagland, Editor-in-Chief
| Reprints
Organizations on the leading edge are also strategically leveraging information technology and data analytics as a key facilitator to continuous performance improvement, particularly on the clinical side

At a time when the leaders of patient care organizations are facing intensifying pressure to shift away from a dependence on volume-based payment and to plunge into value-based care delivery, what strategies can help them lead their organizations to success under new paradigms? With Seema Verma herself, Administrator of the Centers for Medicare & Medicaid Services (CMS), bluntly warning hospital, medical group, and health system leaders that she and her fellow senior federal healthcare officials will be pushing hard to compel providers forward into value-based contracting, IT-facilitated continuous performance improvement strategies are looming large as a critical success factor in the shift to value.

Indeed, speaking during a webinar on August 27 sponsored by the Accountable Care Collaborative, Verma responded to questions about CMS’s effort to push provider organizations to take on two-sided risk in the context of the agency’s accountable care organization (ACO) programs, particularly the Medicare Shared Savings Program (MSSP).

Asked by the webinar host, Mark McClellan, M.D., director of the Duke-Margolis Center for Health Policy and co-chairman of the Accountable Care Learning Collaborative, about provider feedback on the proposed changes to the MSSP ACO program, Verma responded, “I think many people recognize that it’s time to take that next step and it’s time to evolve the program; it’s been six years. We also understand that there may be providers that are not ready. But, our focus is to work with providers that are serious about making the investments and providing better care for lower cost.” What’s more, she intoned, “We’re trying to transition the structure to encourage providers to take on risk because we know that is going to deliver better outcomes.”

And while none of that rhetorical forcefulness—some might even call it saber-rattling—should come as a surprise from Verma, it’s also true that she fully realizes how challenging the overall transition is turning out to be for the vast majority of patient care organizations, which have more-or-less-contentedly been inhabiting a discounted fee-for-service payment world, even as the discounts have progressively bitten more deeply into their operating revenues.

The reality? On the hospital and health system side of the industry, hospital senior leaders long ago shaved off excessive expenses when it came to such areas as the supply chain and facilities management. And what remains to tackle now is the Moby Dick of operations: reworking processes at the core of patient care delivery, in order to achieve significantly improved cost-effectiveness and patient outcomes; everything else has already been tackled. In short, it’s become eminently clear that clinical and operational transformation cannot happen without the thorough reengineering of core care delivery processes.

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...

In that context, larger numbers of hospital and health system (and a few medical group) leaders have plunged ahead over the past decade-plus, and have moved to incorporate the use of formal performance improvement methodologies, among them Lean management, Six Sigma, the Toyota Production System for healthcare, and PDSA (Plan Do Study Act, formerly PDCA, or Plan Do Check Act) cycles of improvement, in order to achieve clinical and operational transformation. In practice, the quality leaders at most patient care organizations have liberally mixed the use of various methodologies, while others have relied primarily on one methodology, but have allowed the blending of concepts from others.

What’s more, the organizations on the leading edge are also strategically leveraging information technology and data analytics as a key facilitator to continuous performance improvement, particularly on the clinical side. Indeed, they are finding IT facilitation to be essential to success in achieving transformational change.

In Asheville, A Comprehensive Push Forward into Value

One of the patient care organizations that has been moving ahead determinedly in its use of IT-facilitated continuous performance improvement strategies is Mission Health, a six-hospital, 11,000-employee health system based in Asheville, North Carolina.

There, Chris DeRienzo, M.D., Mission Health’s chief quality officer, and Dawn Burgard, director of clinical performance improvement, have been helping to lead a comprehensive effort for several years, one that has already borne significant fruit. Back in 2010 and 2011, Mission Health leaders began mapping care delivery processes, adding in an analytics platform in 2013 and 2014. Burgard, who came to Mission Health in 2012, with a master black belt in Six Sigma and a certification in Lean management, and Dr. DeRienzo, who came in 2013, have turbocharged efforts in the organization since then. Among other developments, they early on brought on a cadre of 21 Lean management engineers, known as quality improvement advisors, or QIAs, and have built an enterprise-wide data warehouse.

One key tool that the leaders at Mission Health have built has been a dashboard called the Ambulatory CPM Explorer Dashboard, which is bringing near-real-time data to physicians. Among the accomplishments in the past few years:

  • A 20-percent increase in full sepsis bundle and a 32-percent reduction in mortality from sepsis
  • 12 lung cancer deaths avoided with 37 percent increase in screening
  • 9 fewer rib fracture deaths and $350,000 in reduced direct costs
  • A 42-percent reduction in in-hospital stroke mortality
  • 11,000 more women screened for breast cancer, 6,000 more people screened for colorectal cancer, and a seven-fold increase in depression screening

And, in two specific areas—among numerous others—Mission Health leaders have leveraged performance improvement cycles to build and optimize key initiatives. One has been the creation of the organization’s Readmissions Predictor initiative, which has dramatically enhanced ambulatory care managers’ ability to efficiently predict which patients might be at the highest risk for readmission, following discharge. That initiative began in early 2017, and has been led directly by Dr. DeRienzo and by Mission Health’s CIO, John Brown.

Spending over a year to build, test, and validate the program, Mission Health leaders created a dashboard that uses smart algorithms to provide care managers with up-to-the-minute data every morning at the start of the workday, helping them to determine which individuals, post-discharge, are most likely to end up being readmitted, and allowing them to start their days focusing on those at highest risk for readmission.

A second very important initiative, which began a year and a half ago, has involved applying the Explorer Dashboard to monitor patient flow into and through the emergency department, and to take steps to respond to emerging patient-flow blockages created by surges in patients presenting in the ED. Now, Burgard reports, “We have triggers on our home page, so everyone in the hospital knows what surge status we’re in. And once a new color is triggered”—from a range of four colors (green, yellow, orange, red) that indicate the degree of blockage—"there’s a whole bunch of standard work—a Lean term that involves the standardization of the elimination of variation in processes—that teams and managers are expected to do, depending on surge level,” she says. “That’s the power of standard work. It allows us to get into that predictive space and helps us to become more efficient with the way we staff.” Using this set of processes, patient volume surging that had peaked at 4 percent of patients who left before being seen, in the summer of 2016, is now down to 1 percent, with the ability to see 300 patients every day in the flagship hospital’s ED now a standard volume that has been made the norm.

The core recipe, DeRienzo notes, has included the following: a reliable enterprise data warehouse; a reliable data visualization environment; “more structure in clinical program leadership among physicians, nurses, and administrators”; a cadre of Lean management engineers; and, “trusted advisors.”

At UPMC, Patient Engagement for Improved Outcomes

Numerous quality improvement methodology-infused initiatives are moving ahead as well at the 40-hospital UPMC health system, based in Pittsburgh. There, says Tami Minnier, R.N., M.S.N., UPMC’s chief quality officer, “We use all of them”—especially Lean management, Six Sigma, and PDSA principles and strategies. But, she quickly adds, “Coming into healthcare from manufacturing, I learned early on that healthcare wasn’t quite ready for all the terminology around performance improvement methodologies, so we avoid technical terminology here. I have a black belt in Lean, but I don’t get into the intricacies,” she testifies. “I found that it turned people off. We had people say, ‘We don’t build cars.’”

Instead, Minnier has helped to lead forward a number of initiatives, and, she says, “We use whatever tool makes most sense at the time, and have blended them over time over the 12 years that the Wolff Center has been in existence”—referring to the UPMC Wolff Center for Quality, Safety, and Innovation—“and over time, we’ve raised the bar and have introduced things like run charts, fishbones [the fishbone tool for root cause analysis], some of the tools people find useful. But we don’t say, let’s have a big Kaizen on Tuesday afternoon! We’ve been a bit savvy about how we do it.”

And, as one of her key partners in those endeavors, MaCalus Hogan, M.D., vice chair of orthopedic surgery, and medical director for outcomes and registries at the Wolff Center, says, “I’ve been educated in the Lean environment and learned a lot from Tami and her team. Efficiency is key” in every endeavor, he says. “And in the surgical environment, things are geared around doing things well and efficiently.” Together, Minnier and Dr. Hogan have been leading an initiative that has significantly improved both patient engagement, and improved clinical and satisfaction outcomes, around the entire cycle around total hip and knee replacement surgery, which they and their colleagues have implemented across the six highest-volume total joint replacement surgery facilities in the UPMC system. “We needed to go further in clinical care improvement, encompassing from how we prepare patients, to alignment on who were good candidates,” Minnier explains.

And, Minnier says, “One of the things that we learned early on was that there was pretty inconsistent preparation of patients planning to come in for hip or knee replacement. Some doctors and their offices did this really fantastic job of preparing their patients for surgery, and some didn’t quite have it together. So we did a good current-state assessment, using Lean and PDSA approaches. We looked at the current state of variations, and what types of resources and materials people had in place, and then brought together a new model of change, centered around an orthopedic nurse coordinator in every site. That role was to protect and prepare every patient for surgery, and most importantly, to think about what their care at home would be like after surgery.”

The initiative began three years ago, with the orthopedic nurse coordinators being brought in two-and-a-half years ago. Those coordinators, also referred to as “navigators,” ensure an orderly, comprehensive process to prepare patients and provide them with online education. Leveraging the organization’s patient portal, MyUPMC, office physicians can prescribe educational materials during the office visit, just as they’d prescribe medications. And, she says, “The process improvement of having an ortho nurse coordinator, coupled with the technology support, really allowed patients to arrive at a preoperative phase in a much more prepared, organized manner, to anticipate what would happen when they got to the hospital and how they’d be taken care of.” And, as a result of intensive continuous improvement cycles, “We’ve been able to eliminate pretty much all of the variation,” she testifies. “And every single member of these ortho nurse navigators, they meet on a monthly basis, share each other’s practices, they’ve become a resource group unto themselves. That’s how you perpetuate and sustain change.”

In the context of the joint replacement improvement process, Dr. Hogan and Minnier saw clearly the advantage of Hogan’s being a foot and ankle surgeon rather than being a joint replacement surgeon. As such, he brought into the process a level of credibility as a fellow surgeon; yet at the same time, he was in a different subspecialty, so he could not be seen as a threat to the joint replacement surgeons. And the results have been impressive: consistent educational and preparational processes, improved patient satisfaction, and in many cases, enhanced recovery outcomes.

The Power of Harnessing Analytics

Industry leaders interviewed for this article agree on the core truths about all this: that using formal improvement strategies, of whatever specific type, will yield results; and that part of the power of this to achieve clinical transformation is in effectively harnessing IT and data analytics to facilitate such work.

“In my experience, it doesn’t really matter which methodology you choose, but that you choose an improvement methodology or methodologies, and stick with your strategies; it’s the discipline that matters,” says George Reynolds, M.D., the clinical informatics executive advisor for CHIME (the Ann Arbor, Mich.-based College of Healthcare Information Management Executives), and principal in Reynolds Healthcare Advisers, LLC. Dr. Reynolds, who served as the CMIO at Children’s Hospital & Medical Center, in Omaha, Nebraska, for 11 years, and CIO for the last five years of that tenure, reports that “We did a version of PDCA [Plan Do Check Act—an earlier version of Plan Do Study Act], which is very easy to teach, but lacks the rigor and the discipline of Lean and Six Sigma. We would do well [at Children’s], but it was hard to maintain the changes.”

Meanwhile, Dr. Reynolds says firmly, leveraging data and analytics to power performance improvement cycles is “absolutely central to everything you do. And it doesn’t necessarily have to be really fancy bells and whistles, though I love fancy bells and whistles. You can do a lot with an Excel spreadsheet. You can do a lot with some fairly simple tools. But the more advanced tools become valuable” as organizations move forward into deeper and broader efforts.

Early on in the Proverbial Journey of 1,000 Miles

What remains disconcerting is how far behind most U.S. patient care organizations are starting out, says Robin Czajka, service line vice president for cost management at the Charlotte-based Premier Inc. Asked where she thinks the healthcare industry is, if this phenomenon could be compared to the proverbial journey of a thousand miles, the Chicago-based Czajka says that “I would say that we’re at the very beginning of it, frankly, having been in the industry for 25 years. You see pockets of great performance, and areas where we haven’t made any progress at all,” she says. “Some organizations are short of staff and mired in taking care of increasingly sick patients. So this needs to be a top priority. And we’re looking at a 5-percent growth year-over-year” in hospital costs. “The Medicare fund will be insolvent if we keep on this trajectory.”

What’s more, says Mary Frances Butler, a senior adviser at the Chicago-based Impact Advisors consulting firm, the level of progress in this area “will depend on the type of hospital.” There is a continuum of advancement, she notes, “from small community hospitals, all the way up to the mega-systems like Intermountain and Geisinger [the Salt Lake City-based Intermountain Health and the Danville, Pa.-based Geisinger Health], who have been at it a long time. Intermountain is an example of a leader in this. And, to the extent that leader organizations have been able to facilitate conversations through the C-suite and into the IT group, to get out of their silos,” they’ve made greater progress, she notes.

Premier’s Czajka has mixed sentiments with regard to the mixing or blending of specific methodologies. “It’s both good and bad; you can create some kinds of success, but you do lose some things; I’ve personally seen Lean be effective when done rigorously,” she says. “But as long as it’s cyclical, monitored, and sustainable, and as long as there are checks and balances,” any combination of methodologies can be made to work well, she says. The absolutely critical success factor? “Success in this area is always data-driven,” she insists. “And with Six Sigma, you take data over time and look at it and act. A lot of organizations will see a blip, for example, bed sores, and will react to it. But it may turn out to be a special-cause variation, maybe they got an unusual surge of admissions from a nursing home or something. When you start to employ a system like Lean, problem solvers become problem framers. So you need to look carefully at the data and analyze it, and act over time.”

The Power of Data-Focused Teams

One lesson shared by those in the trenches is the power of creating and nurturing purpose-specific teams focused intensively on the management of data to power performance improvement, particularly in the clinical area. Oscar Marroquin, M.D., a practicing cardiologist and epidemiologist in Pittsburgh, has been helping to lead a team of data experts there. That team, of about 25 data specialists, was first created five years ago. Of those, half are IT- and infrastructure-focused, and, says Dr. Marroquin, “The rest are a team of folks dedicated to data consumption issues. So we have clinical analysts, data visualization specialists, and a team of data scientists who are applying the right tools and methods, spanning from traditional analytical techniques to advanced computational deep learning and everything in between. Our task is to use the clinical data, and derive insights”—and all 12 clinically focused data specialists report to him.

And that work—“allowing people to ask questions to generate opportunities”—has paid off handsomely. Among the advances has been the creation of a data model that predicts the chances that patients who are being discharged will be readmitted. The model, based on the retrospective analysis of one million discharges, is also helping case managers to more effectively prepare patients for discharge, specifically by ensuring that patients being discharged are promptly scheduled for follow-up visits with their primary care physicians. “If those patients are seen within 30 days of discharge,” he notes, “there’s a 50-percent reduction in their 30-day rate of readmission.” The program is now active in six UPMC hospitals.

What it Really Means to be Data-Driven

Those industry leaders interviewed for this article are agreed on what healthcare IT leaders should know both about the adoption of performance improvement methodologies generally, as well as about the leveraging of IT and data to achieve success in clinical and operational transformation.

“If you’re going to embark on a Lean Six Sigma-driven journey, it rises and falls based on leadership,” says Mission Health’s Burgard. “We know that the methodologies work. But I always say, Lean is not a set of tools, it’s a mindset for how you’ll transform your organization. The same thing is true with technology. It all rises and falls on leadership. And senior leaders need to understand the methodology and the tools. That applies to technology, too.”

“I’ve been really impressed with the degree of partnership of our CIO John Brown, with our PI team,” says her colleague DeRienzo. “When I think about continuous improvement, there’s so much overlap between the improvement processes and the data processes. And by driving alignments across the entire system, including across the different teams, we’ve been able to make much broader progress.”

Importantly, says Premier Inc.’s Czajka, “It’s crucial to accept that data shouldn’t be the enemy of the good. The data is never going to be perfect,” she says. “Just make sure it’s directionally accurate.” What’s more, she says, “You need to train your people to use the data correctly. I can’t tell you how many times I meet with clients and they have these great data systems they’ve purchased, but no one is trained to work well with it. And,” she says, “figure out the data points that will actually drive improvement. I went into a member hospital that had about 100 data points they were asking people to focus on, in a dashboard. You can’t ask people to do that.” Working with leaders at that hospital, she was able to get them to narrow down those 100-some data points to 11 that could be focused on, for process improvement.

In the end, says UPMC’s Marroquin, “If we all are serious about transforming the way we care for patients, we need to do it in a data-driven way. There has to be a philosophical belief and commitment to do that, and then you have to create a team that’s dedicated to this work. I don’t think this is achievable in an ad hoc way.” Finally, he says, “This work is not for the faint of heart; it takes time and effort, but if you have the philosophical belief and institutional commitment, it’s doable.”


Related Insights For: Analytics

/article/analytics/walk-you-can-run-predictive-analytics

You Have to Learn to Walk Before You Can Run With Predictive Analytics

November 11, 2018
by David Raths, Contributing Editor
| Reprints
Health systems report obstacles in turning their big data into actionable insights

The title of a recent webinar says all you need to know about predictive analytics in healthcare: “Within Sight Yet Out of Reach.”

The Center for Connected Medicine, jointly operated by GE Healthcare, Nokia, and UPMC, put on the webinar and partnered with HIMSS on a survey on the state of predictive analytics in healthcare.

The survey of 100 health IT leaders found that approximately 7 out of 10 hospitals and health systems say they are taking some action to formulate or execute a strategy for predictive analytics. But despite the buzz and potential, there are obstacles for health systems that want to turn their big data into actionable insights.

Although 69 percent said they are effective at using data to describe past health events, 49 percent said they are less effective at using data to predict future outcomes. They cite a lack of interoperability and a shortage of skilled workers as barriers. “They want to put all that data to work to provide insights as we deliver care, but it is not an easy task,” said Oscar Marroquin, M.D., chief clinical analytics officer at UPMC. “They are having trouble getting access to the data in useful and standardized formats and don’t have the people in place to apply machine learning techniques.”

The top five use cases cited in the survey are:

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...

• Fostering more cost-effective care

• Reducing readmissions

• Identifying at-risk patients

• Driving proactive preventive care

• Improving chronic conditions management

UPMC’s journey into the analytics space was jump-started by an institutional commitment to building the analytics program and a recognition that it needed to be a more data-driven organization. “We were never able to consume our data to drive how we deliver care until we had a dedicated team to do analytics,” Marroquin said. “Traditionally these functions were done as a side job by team members in IT systems. We have found having a dedicated team is absolutely necessary.”

Mona Siddiqui, M.D., M.P.H., chief data officer at the U.S. Department of Health & Human Services, says she is focused on the interoperability aspect across 29 agencies. “We are looking at how we are using data across silos to create more business value for the department,” she said. “We don’t have that infrastructure in place yet,” which leads to one-off projects rather than tackling larger priorities. She is focusing on enterprise-level data governance and interoperability structures. “I think the promise of big data is real, but I don’t think a lot of organizations have thought through the tough work required to make it happen. Practitioners start to see it as buzzword rather than something creating real value. There is a lot of work that needs to happen before we see value coming from data.”

Noting the survey result about human resources, she added that “the talent pool is an incredible challenge. While we talk about sharing data and using it for business intelligence, we don’t resource our teams appropriately to fulfill that promise.”

She said the move to value-based care has made predictive analytics more important to health systems. “It is a data play from the ground up,” and now we are starting to see the real impact in terms of managing chronic conditions. “More organizations like UPMC are seeing this is about data and measurement and bringing in not just data they have, but resources and data they may not have had access to previously.”

Travis Frosch, senior director of analytics at GE Healthcare, said that hospitals generate petabytes of data per year, yet only 3 percent is tagged for analytical use later on. “So 97 percent goes down the drain,” he added, suggesting that organizations need to start small. “If you are an organization that does not have maturity in analytics, start with traditional business intelligence to build the trust and foundation to move toward higher level of analytics maturity,” Frosch said. “Pick projects that don’t require tons of data sources. If you get a good a return on investment you can open up the budget to further your analytics journey. But you have to have a unit in place to measure the impact.”

 


See more on Analytics

betebettipobetngsbahis bahis siteleringsbahis