We at Healthcare Innovation were once again thrilled with the extraordinary quality of submissions we received from innovating patient care organizations across the U.S. In addition to the four winning teams this year, our editorial staff also selected six organizations as semifinalists. Below are descriptions of these teams’ initiatives.
Allina Health dashboards help coach physicians on EHR optimization
Most large healthcare provider organizations have teams working to optimize their electronic health record (EHR) use, but Allina Health in Minnesota is particularly aggressive in its efforts to help clinicians get the most out of the EHR. “We have a philosophy of keeping things simple and keeping the computer out of the way of that provider/patient interaction,” says David Ingham, M.D., medical director of ambulatory services. Since early 2018, Allina informaticists have been creating dashboards that take provider efficiency profile (PEP) data from Epic and present it in a much more usable format.
Ingham uses a metaphor of a coach helping a golfer improve his or her swing to describe what his team is doing. “We really do use it in a coaching fashion, at least as a jumping-off point,” he says. Allina’s performance support trainers are the front line for ongoing training. It used to be if they have 10 minutes with a provider, they might spend eight of the 10 minutes figuring out what they needed help with. “But if they have data on provider tendencies,” he explains, “it allows them to focus on trouble spots and not on the things they are already good at.”
Allina’s Clinic Provider Efficiency Dashboard (CPED) report includes 15 key indicators such as total EHR time per patient and usage of specific macros called SmartTools. By deploying interventions, measuring impact, and then adjusting or expanding the intervention accordingly, Allina has seen improved provider engagement, higher utilization of important SmartTools, and less time spent in the EHR. “By helping them build SmartTools that work for them, you can save them a little time evesy day,” Ingham says.
Providers can look at their own CPED performance compared to the average of their peers. Allina has found that primary-care physicians are spending 30 seconds less per patient after hours writing notes, and at least part of that improvement is attributable to CPED, Ingham says. That may not sound like much of a change, but it means that if a busy physician sees 20 patients per day, she now has 10 additional minutes of time each evening that previously was spent in the EHR.
Technology bolsters creation of Compass Medical’s lung cancer screening program
According to the American Cancer Society, “Lung cancer is the leading cause of cancer death among both men and women.” But there is hope. Low-dose CT scans can help detect lung cancer at its earliest stage, when it’s most treatable. The challenge is to identify those patients at high risk and encourage them to get screened.
Starting in May 2017, Compass Medical, a comprehensive healthcare organization south of Boston, rolled out a lung cancer screening program and developed workflows in its EHR to make it easy for providers to support the program.
The guidelines around offering a low-dose CT scan in high-risk populations have been progressively developed since 2011, explained Michael Myers, M.D., Compass’ chief medical officer. The Center for Medicare & Medicaid Services (CMS) covers the CT scans for a population of patients between 55 and 77 who meet certain heavy smoking criteria over many years, were asymptomatic and had no prior chest CT in the preceding 12 months. “When a patient meets those critieria, they are thought to be in a high-risk pool. Those are the folks you want to screen,” Myers says. “The challenge is finding those people.”
Setting up screening programs for breast, cervical or colorectal cancer is easier, because it basically involves age or sex cutoffs. “But when you are adding smoking status and current smoker and no symptoms and all these other factors, that is where our EHR system really helped,” he says.
Christine Machado, Compass’ EHR manager, says her team created a template in the EHR with the guided questions for a medical assistant to ask to help determine eligibility. They also created the order set for shared decision making and radiology referrals. She adds that the EHR team transformed the CMS lung cancer screening eligibility requirements into a practical and complete clinical operational workflow for recording these data points within the EHR.
Once patients are identified as qualified and agreeable to this specific treatment plan, the low-dose CT order is placed in the patient’s EHR with just two clicks. Since May 2017, the medical group has identified 1,800 patients eligible for the program and 1,000 of those patients received a low-dose CT scan. Of those 1,000 patients that Compass Medical has scanned, it has confirmed 13 lung cancers, diagnosed five incidental non-lung cancers and has 43 unique patients with suspicious nodules found through the screening who it is tracking closely. Compass Medical was recently named a “Screening Center of Excellence” by the Lung Cancer Alliance.
Deborah Heart and Lung Center fine-tunes its discharge process
As a specialty hospital providing cardiovascular and pulmonary services, Deborah Heart and Lung Center treats some of the highest acuity patients in New Jersey. Although the organization has typically received high patient satisfaction scores, last year a team of clinical and administrative leaders came together to improve the discharge process by making it more patient-centric and ensuring that patients aren’t unnecessarily detained in various areas throughout the center.
Richard Temple, vice president and chief information officer, and Lynn McGrath, M.D., chief medical officer and vice president of medical affairs, spearheaded an initiative to track and analyze the timeliness of Deborah’s patient discharge process. One goal was to increase the number of patients discharged by 10 a.m. each day. It is a win for the patients in terms of satisfaction and frees up beds fTo study the issue, the team created customized dashboards using the business and clinical analytics (BCA) solution offered by their EHR vendor Meditech. “I see problems in terms of how we can track them using data to measure improvement,” Temple says. “I realized we could use this BCA tool to push the information out to the right people at the right time. It provided visibility and transparency, and we could break things out by doctor and by unit.”
Using the new dashboard, an upgrade from the previous method of using Excel spreadsheets, Deborah’s leaders could drill down into individual discharges to see what happened. The data could be broken down by the hour, discharging physician, inpatient service, and day of the week, with the ability to drill down to patient detail. The team also tracked discharges that occurred before 11 a.m., to determine if they had missed their goal by a significant amount of time or by mere minutes.
With access to so much data, the team was now able to identify reasons when they missed the 10 a.m. goal. For instance, lack of good transportation options was one challenge identified. “We worked to improve communication with the family the day before to make sure someone is there to pick them up in the morning. Being able to look at the data by unit and by doctor, and being able to classify reasons for missing the goal gave us a lot of power in terms of zeroing in,” Temple says.
Using the high-level insight provided by this dashboard, Deborah achieved a tenfold increase in the number of patient discharges before 10 a.m. in less than four months. Temple says having the right people in the group and conducting meetings the right way is a huge part of the success. But the timely data is essential. “There is nothing like being able to get a data feed out of your EHR data repository and graph, track and trend it. The Meditech BCA tool is powerful and makes it easy to get information to the people who need to see it.”
Flagler Hospital leveraging AI to bolster its care pathways process
(Former Healthcare Innovation Associate Editor Heather Landi contributed to this story).
Like many other hospitals and health systems, Flagler Hospital, a 335-bed community hospital in St. Augustine, Fla., had a board-level mandate to address its unwarranted clinical variation with the goal of improving outcomes and lowering costs, says Michael Sanders, M.D., Flagler Hospital’s chief medical information officer (CMIO).
He says that traditional methods of addressing clinical variation management have been inefficient, as developing care pathways often takes up to six months or even years to develop and implement. “By the time you finish, it’s out of date,” Sanders says. “There wasn’t a good way of doing this, other than picking your spots periodically, doing an analysis and trying to make sense of the data.”
Sanders says he was intrigued by advances in machine learning tools and artificial intelligence (AI) platforms capable of applying advanced analytics to identify hidden patterns in data. Working with Palo Alto, Calif.-based machine intelligence software company Ayasdi, Flagler Hospital initiated a pilot project to use Ayasdi’s clinical variation management application to develop care pathways for both acute and non-acute conditions and then measure adherence to those pathways.
Flagler targeted their treatment protocols for pneumonia as an initial care process model. The AI tools from Ayasdi revealed new, improved care pathways for pneumonia after analyzing thousands of patient records from the hospital and identifying the commonalities between those with the best outcomes. The application uses unsupervised machine learning and supervised prediction to optimally align the sequence and timing of care with the goal of optimizing for patient outcomes, cost, readmissions, mortality rate, provider adherence, and other variables.
The hospital quickly implemented the new pneumonia pathway by changing the order set in its Allscripts EHR system.
The AI application uncovered relationships and patterns that physicians either would not have identified or would have taken much longer to identify, Sanders says. For instance, the analysis revealed that for patients with pneumonia and COPD, beginning nebulizer treatments early in their hospital stays improved outcomes tremendously, hospital leaders report.
As a result, for the pneumonia care path, Flagler Hospital saved $1,350 per patient and reduced the length of stay (LOS) for these patients by two days, on average. The hospital also reduced readmission by seven times—the readmission rate dropped from 2.9 percent to 0.4 percent, hospital officials report. The initial work saved nearly $850,000 in unnecessary costs—the costs were trimmed by eliminating labs, X-rays and other processes that did not add value or resulted in a reduction in the lengths of stay or readmissions.
“Those results are pretty amazing,” Sanders says. “It’s taking our data and showing us what we need to pursue. That’s powerful.”
Dashboards guide process change to improve hospital-acquired VTE rates
For several years, PIH Health, a two-hospital regional healthcare network, had seen little improvement in its hospital-acquired venous thromboembolism (VTE) rates. In 2016, when the Agency for Healthcare Research and Quality (AHRQ) came out with its new guide, “Preventing Hospital-Associated Venous Thromboembolism, A Guide for Effective Quality Improvement,” it spurred Whittier, Calif.-based PIH Health’s efforts to change its entire VTE prevention strategy, with a goal of reducing its hospital-acquired VTE rates by 20 percent.
Previously, the VTE risk assessment was performed by the floor nurse after the patient was admitted, using the Caprini scoring tool. This posed a number of challenges, PIH Health said. Not only was the tool time-intensive to fill out (roughly 30 questions total), but the hospitalists were often placing admission orders in the emergency department, leading to placement of VTE prophylaxis orders before the VTE risk assessment was completed, explains Davis Lee, M.D., CMIO. PIH decided to completely change this process.
Despite revamped efforts, PIH Health was not seeing the improvements it had expected, and realized that it needed a better way to monitor outcomes and processes. With assistance from Allscripts, they created new interactive dashboards to help the front-line staff, as well as quality and administrative leadership departments access real-time data.
The real-time dashboard of admitted patients displays the physician VTE risk assessment score, alongside the nursing VTE risk score, as well as the current VTE prophylaxis orders. They measured the appropriateness of the prophylaxis orders as well as the use of “bleeding risk” as a contraindication for pharmacologic prophylaxis. A physician scorecard was developed that allowed PIH Health to track, by physician, the risk assessments performed, and compliance of completing it within 24 hours.
Lee stresses the importance of having real-time data in the dashboards. “You want to be able to take the appropriate actions while the patient is still in house,” he says. “That is the only time when you are going to make a tangible difference in patient care. Otherwise you are playing catchup constantly to see if changes work. Now we can see if a risk assessment wasn’t done or if they didn’t put a patient on the appropriate prophylaxis. We can make changes in real time. That is going to change outcomes, rather than working with retrospective data.”
PIH Health’s’ hospital-acquired VTE rates are now down from 3.9 to 0.74 per 1,000 visits (average January to September 2018). The 81 percent reduction easily passed its goal of 20 percent.
Nevada expands ambitious population health study
Despite leading the country in growth and innovation, project leaders note that Nevada ranks 47th in the nation in terms of health. A collaboration between Reno-based Renown Health and the Desert Research Institute (DRI), the Healthy Nevada Project is a novel population health study to understand and address some of the state’s health most pressing health issues. By examining genetic, clinical, environmental and socioeconomic data, in combination, the goal is to better understand the complex interplay between these factors and related effects on the health of Nevadans.
The pilot phase of the Healthy Nevada Project launched in September 2016, enrolling 10,000 Nevadans in just 48 hours, and within 60 working days, each participant had donated a DNA sample for genotyping. “Some people refer to this as the fastest clinical trial enrollment in the history of the country,” says Anthony Slonim, M.D., president and CEO of nonprofit Renown Health. “We opened it up, not to their doctors who had a hundred other things going on, but directly to people and said all you have to do is show up, and they did.”
The project completed DNA sequencing of nearly 40,000 people in 2018, bringing its total enrollment to 50,000 people, approximately 10 percent of northern Nevada’s population and including a demographically representative set of Renown Health’s patient population.
Researchers are using an SAS analytics-powered platform to analyze population health risks from patient variables such as gender, age, and personal or family health history. The platform is being used to model public health risks ranging from disease and illness to the effects of environmental factors such as air quality. For example, they are working to understand how environmental factors can help predict who may be at risk, allow for quicker diagnoses, and encourage the development of more precise treatments.
“The state has partnered with us so we could get the publicly available data, including from birth and death registries, put them all in one data warehouse and find those trends and patterns to make our community healthier,” Slonim says.
The pilot phase concluded in 2018 and in March of that year, Nevada Gov. Brian Sandoval announced the study’s expansion, opening enrollment to an additional 40,000 participants. Based on the findings of the study’s pilot phase, care providers and scientists have begun working on a number of clinical programs and scientific studies focused specifically on Washoe County’s high age-adjusted death rates for heart disease, cancer, and chronic lower respiratory disease.
Slonim is a physician, but he also has a doctorate in public health. “For me this project encapsulates both of those educational experiences. As a physician, one patient, one family at a time is where my focus is. As a public health official, the population, the community, and the region are my focus. Somewhere in the middle is where this project sits, delivering results to both sides of that equation.”
The next phase of the project is to expand to southern Nevada in 2019. Slonim is preparing a TEDx talk at the University of Nevada-Reno in which he plans to discuss expanding the concept to other states in what is calling the Healthy USA project. “I’m currently in talks with five health systems around the country to help us launch this in their states,” he says, “under the guise of the Healthy USA project.”