Length of stay (LOS) is an essential indicator of hospital operational efficiency. Albany Med compared its performance with benchmark data and determined that it could improve inpatient LOS. By convening a multidisciplinary team of providers committed to decreasing hospital LOS and leveraging its data and analytics platform, Albany Med was able to uncover underlying issues causing unnecessary extended hospital stays and substantially reduce LOS.
Enterprise Data Warehouse / Data Operating System
Texas Children’s Hospital knew that improving data access was key to driving improvements and sought to improve analytics adoption and democratize its data. By focusing on developing a culture of data access and sharing, Texas Children’s has shifted its data and analytics culture, establishing the foundation required for it to continue to advance its analytics adoption, including engaging in predictive analytics. Leaders and employees are actively investigating and sharing data, and operations are more data-driven than ever before.
Patients shouldn’t have to make difficult medical decisions on their own, nor should they feel coerced into making a specific choice; it’s a fine balance. Read how Allina Health’s shared decision-making program has helped patients deal with this delicate process.
Hospital readmissions carry significant financial costs and are associated with negative patient outcomes. With the help of data analytics, Mission Health developed its own predictive model for assessing readmission risk, aimed at preventing readmissions and improving outcomes for patients.
Contemporary colorectal surgery is often associated with long LOS, high costs, and surgical site infections (SSI) approaching 20 percent. Much of the LOS variation is not attributable to patient illness or complications, but most likely represents differences in practice style. Successfully reducing SSI requires a multimodal strategy under the supervision of numerous providers with high compliance across the spectrum.
Allina Health was using established, evidence-based clinical guidelines, yet clinical variation remained high across pre-arrival, preoperative, intraoperative, and postoperative care areas, leading to substantial variation in LOS, cost of care, and the patient experience. To ensure greater consistency, Allina Health developed an enhanced recovery program (ERP) for patients undergoing elective colorectal surgery, which built standard protocols into the EHR to address elements of care from pre-arrival through post-discharge.
To facilitate the program and monitor performance, Allina Health developed an ERP analytics application with an administrative dashboard to easily visualize first-year results:
78 percent relative reduction in elective colorectal SSI rate.
19 percent relative reduction in LOS for patients with elective colorectal surgery.
82.4 percent utilization of preoperative and postoperative order sets, increasing the consistency of care and reducing unwarranted variation.
Total Hip (THA) and Total Knee (TKA) Arthroplasty are the most prevalent surgeries for Medicare patients, numbering over 400,000 cases in 2014, costing more than seven billion dollars annually for the hospitalization alone. Today, more than seven million Americans have hip or knee implants, and the number is rising. Furthermore, substantial variation in the cost per case has raised questions about the quality of care. At Thibodaux Regional Medical Center, total joint replacement for hips and knees emerged as one of the top two cost-driving clinical areas with variation in care processes.
To address this, Thibodaux Regional maintained its focus on the IHI Triple Aim while developing organizational and clinical strategies to transform the care of patients undergoing THA and TKA. It commissioned a Care Transformation Orthopedic Team that set multiple outcome goals. Among its many efforts, the team established standard care processes, created an educational program, redesigned order sets and workflows, and deployed a joint replacement analytics application.
Thibodaux Regional reduced variability and decreased costs significantly while maintaining high levels of patient satisfaction:
76.5 percent relative reduction in complication rate for total hip and total knee replacement.
38.5 percent relative reduction in LOS for patients with total hip replacements.
23.3 percent relative reduction in LOS for patients with total knee replacement.
$815,103 cost savings, achieved in less than two years.
Machine Learning, Predictive Analytics, and Process Redesign Reduces Readmission Rates by 50 Percent
The estimated annual cost of readmissions for Medicare is $26 billion, with $17 billion considered avoidable. Readmissions are driven largely by poor discharge procedures and inadequate follow-up care. Nearly one in every five Medicare patients discharged from the hospital is readmitted within 30 days.
The University of Kansas Health System had previously made improvements to reduce its readmission rate. The most recent readmission trend, however, did not reflect any additional improvement, and failed to meet hospital targets and expectations.
To further reduce the rate of avoidable readmission, The University of Kansas Health System launched a plan based on machine learning, predictive analytics, and lean care redesign. The organization used its analytics platform, to carry out its objectives.
The University of Kansas Health System substantially reduced its 30-day readmission rate by accurately identifying patients at highest risk of readmission and guiding clinical interventions:
39 percent relative reduction in all-cause 30-day.
52 percent relative reduction in 30-day readmission of patients with a principle diagnosis of heart failure.
Health equity means that everyone has an equal opportunity to live the healthiest life possible – this requires removing obstacles to health. The U.S. ranks last on nearly all measures of equity, as indicated by its large, disparities in health outcomes. Illness, disability, and death in the United States are more prevalent and more severe for minority groups. Health inequities persist in Minnesota as well, which motivated Allina Health to take targeted actions to reduce inequities.
Allina Health needed actionable data to identify disparities and to reduce these inequities. This came in the form of REAL (race, ethnicity, and language) data, which Allina Health analysts used to visualize how health outcomes vary by demographic characteristics including race, ethnicity, and language. To understand the root causes of specific disparities as well as to identify solutions within their sphere of influence as a healthcare delivery system, Allina Health consulted the literature and also consulted patients, employees and community members. Then Allina Health created appropriate interventions based on this information.
As a result, Allina Health created an awareness of the health inequities among its patient populations, as well as effective approaches to breach the barriers that were preventing these patients from getting the care they needed. While much work remains in this long journey to achieve health equity, Allina Health has taken some significant steps forward, including:
Three percent relative improvement in colorectal cancer (CRC) screening rates for targeted populations, exceeding national CRC screening rates by more than ten percentage points.
REAL data embedded in dashboards and workflow to easily identify and monitor disparities.
Research shows that despite an increase in the number of improvements in clinical, cost, and operational outcomes, there is a lack of sustained improvements. Some of the key challenges can be access to the data and analytics, and adherence to data-driven clinical standards, things the Allina Health Spine Clinical Service Line (CSL) clinical leadership team experienced.
By providing widespread access to the data and analytics, the Spine CSL at Allina Health has been able to continue its reduction in LOS and further improve its reduction in complications, all while increasing cost savings and achieving pay-for-performance incentives.
$1 million in pay-for-performance incentives received.
More than $2 million in supply chain savings, a result of data-driven clinical standardization.
31 percent of expected complications avoided.
22 percent relative reduction in surgical site infections.
Every three seconds, someone in the United States will need a blood transfusion, which adds up to nearly 17 million blood components transfused annually. Yet, evidence shows that up to 60 percent of red cell transfusions may not be necessary. In 2011, Allina Health, a healthcare delivery system that serves Minnesota and western Wisconsin, had a wide variation in transfusion practices throughout the system and a transfusion rate that was 25 percent above national benchmarks. In an effort to improve outcomes of high-risk transfusions, Allina Health turned to its data to develop an evidence-based blood conservation program aimed at reducing costs and saving valuable blood resources.
$3.2M decrease in annual blood product acquisition costs since 2011
30,283 units saved annually
111 units of red cells saved per 1000 inpatient admissions
Today’s healthcare industry, in which a lack of insight into clinical variation has contributed to increased expenses, has significant opportunities to use data and analytics to improve outcomes and reduce costs. As part of its ongoing commitment to improve clinical value, Allina Health has employed a systemwide process to identify, measure, and improve clinical value. The health system has been able to quantify the value of clinical change work to improve outcomes, while reducing costs and increasing revenue for reinvestment in care.
Allina Health achieved the following meaningful results with this collaborative, data-driven opportunity analysis process:
Identified nearly $33 million in potential cost savings for the first three quarters of 2017.
Achieved over $10 million of confirmed savings during the first three quarters of the year.
Elevated discussions of cost concerns, leading to the development of standard processes, and significantly reducing unwarranted clinical variation.
With the current state of uncertainty facing healthcare organizations, survival requires unprecedented agility when it comes to acquiring and responding to meaningful, strategic information. After adopting the Health Catalyst Analytics Platform, including the Late-Binding™ Data Warehouse and broad suite of analytics applications, Partners HealthCare promoted a philosophy of expanded access to the enterprise data warehouse (EDW) to increase adoption and self-service analytics to improve patient care and outcomes.
Partners needed widespread adoption of the EDW so that information could be meaningfully incorporated into strategic, clinical and operational decision making to support patient care. This meant that users who had a legitimate need to access data to support their job function were encouraged to seek access to the EDW. The organization continues to focus on further increasing the effectiveness of this strategy by ensuring that users have the means to acquire the skills, knowledge, and support they need to effectively use data stored in the EDW.
243 percent increase in user base—achieved over a two-year period (700+ unique users).
More data available to a broader audience than ever before.
Physician time to access data reduced from weeks to clicks.
87 percent of user community satisfied with the effectiveness of communication provided to support their use of the EDW.
Mixed reviews of the effectiveness of pay-for-performance programs leave hospitals wondering how to affect meaningful change in patient care and outcomes. However, MultiCare’s experience with focused improvement efforts supported by analytics for pneumonia, sepsis, and women’s care showed that better data consistently leads to better patient outcomes.
Committed to improving population health, and informed by their experience as well as national trends and outcomes, MultiCare formed a new partnership with Health Catalyst, a next-generation data, analytics, and decision support company. The shared risk partnership generated an improvement framework and governance structure formed around a Shared Governance Committee which is responsible for prioritizing, resourcing, and aligning improvement initiatives across MultiCare. The committee and the projects it ultimately approves are informed by data-driven opportunity analysis and ongoing analytics support. This partnership and structure have achieved the following:
Strategic alignment of outcomes goals across the organization.
Established an Analytics Center of Excellence.
Integrated financial data into outcomes improvement initiatives.
Effective data integration enables high value through more strategic, data-driven decision-making, while faster data acquisition feeds and speeds up the process. Orlando Health, one of Florida’s most comprehensive private, not-for-profit healthcare networks, recognized the need for effective data integration to successfully manage to the organization’s changing business needs. The health system needed the ability to rapidly acquire and link disparate healthcare data sources in various ways in order to answer clinical and business questions.
Leaders at Orlando Health needed a data warehouse that better met their needs. They determined that switching from an early binding data process to a late-binding process would provide greater flexibility and expand their access to critical data, with shorter data acquisition times.
With the new EDW, Orlando Health achieved the following efficiencies:
245 fewer days and 1.0 less full time employee (FTE) needed to integrate encounter billing summary system data.
56 fewer days and 0.4 less FTE needed to integrate Infection control system data.
99 percent reduction (90 days saved) in the amount of time needed to implement system enhancements.
98 percent reduction in the work hours needed to incorporate system enhancements.
Clinical variation can be frustrating for patients and their families, often leaving the impression that healthcare team members are not on the same page and don’t agree on the plan for the patient’s diagnosis or treatment. It is also costly—the Institute of Medicine estimates that $265 billion (30 percent) of healthcare spending is waste that directly results from clinical variation.
To reduce unwanted variation, Texas Children’s Hospital invested considerable resources to develop clinical standards tools, including evidence-based order sets; however, demonstrating the effectiveness and utilization of those guidelines, pathways, and order sets had been daunting. To that end, Texas Children’s deployed an analytics platform from Health Catalyst to aggregate and analyze the data needed to perform both of these critical functions.
$2,401 reduction in cost per patient with order set utilization, and an 8.4-day difference in average length of stay (LOS).
$15 million reduction in total direct variable costs in Fiscal Year 2015, $32 million anticipated reduction in Fiscal Year 2016 at the current order set usage rate, and a potential $64 million annual reduction with a hypothetical 80 percent order set usage rate.
1,629 percent return on investment (ROI).
When healthcare information systems don’t talk to each other, countless inefficiencies and patient safety issues may arise.
Community Health Network (CHNw) believes in delivering outstanding care to every patient. In order to minimize patient safety risks and inefficiencies resulting from using different EHRs, CHNw embarked on a journey to integrate its healthcare information technologies. After implementing a Late-Binding™ Data Warehouse from Health Catalyst that integrates all key data sources, CHNw now has a consistent and comprehensive perspective for multiple patient encounters across the enterprise. It has achieved the following results:
Data from multiple EHR vendors, including four inpatient EHRs and two ambulatory EHRs, plus five transactional systems—HR, patient experience, patient safety, finance, and supply chain— were integrated within 12 months.
More than 55,000 data elements and over 18 billion rows of data were incorporated.
Patient-to-patient matching was implemented for over one million patients across the four inpatient EHRs. This is vital for managing patient populations.
Operational efficiency was improved by 70 percent, with data architects spending an estimated 15 percent of time supporting interfaces compared to an estimated 40-50 percent before the integration. In one example, CHNw linked its ERP/costing system to the EDW’s EHR source marts with just a single interface; previously, this would have required building separate interfaces for all six EHRs.
Improving clinical outcomes is good for patients and good for health systems. In fact, Allina Health’s focus on data-driven outcomes improvement realized a total financial improvement of $125 million in a single year.
Allina embraced the mandate of achieving the Triple Aim: improving the quality and cost of care, as well as the patient experience. To achieve this goal, Allina’s leaders recognized that they would need to realign their strategies, organizational structures, and management practices. Confident that data would help the health system improve the quality of patient care and reduce costs, they implemented a data-driven performance improvement strategy.
The results are astounding. This strategy has achieved financial improvements for the health system of $100+ million per year, four years running, while also advancing Allina Health’s Triple Aim goals of improved clinical outcomes and a better patient experience through dozens of improvement initiatives.
Patient Identification and Matching—An Essential Element of Using an Enterprise Data Warehouse to Manage Population Health
In a healthcare industry transitioning to value-based reimbursement and population health management (PHM), matching patients accurately to their care events across multiple sites of care and sources of information is becoming ever more important. Being able to accurately track utilization of services for a particular patient, patient population, or provider is fundamental to the strategies underlying effective population health management. Partners HealthCare developed an effective patient matching solution for more than 10.5 million patients achieving a 20 percent improvement in patient matching accuracy and a 96-99 percent high-risk patient matching rate. This has allowed the organization to accurately “flag” high risk patient populations and better manage risk under risk-based contracts.
As the healthcare industry rapidly evolves, implementing an enterprise data warehouse has become essential both for population health management and economic survival. While this requires building analytics competency across the enterprise, once adopted, the benefits are abundant—from improved patient outcomes to reduced waste and costs. To rapidly gain value from this platform, healthcare organizations should follow an implementation strategy that, before anything else, identifies the problems analytics is intended to solve. It should also place as much emphasis on people and processes as it does technology. Partners HealthCare is an example of how implementing a data warehouse can quickly leverage analytics across the enterprise to achieve value with high end-user engagement and satisfaction.
The Enterprise Data Warehouse (EDW): Creating the Foundation for Effective Healthcare Improvement Analytics
Population health management and value-based care has arrived. However, many healthcare organizations don’t have a single source of truth for their data, nor can they easily access their information. In the absence of integrated data visibility, many hospitals are relying on manual workarounds that can take months, and sometimes even years to implement—and in the end, may still fall short of delivering the level of insight needed. Learn how Partners HealthCare consolidated its disparate data warehouses, incorporating more than 27,000 data elements from multiple sources systems—and implemented on time and on budget. Partners’ enterprise data warehouse now serves as the analytics foundation for its overall value strategy.
Effective Healthcare Data Governance: How One Hospital System is Managing its Data Assets to Improve Outcomes
As healthcare invests in analytics to meet the IHI Triple Aim, data has become its most valuable asset—and one of the most challenging to manage. Healthcare organizations must integrate data from a complex array of internal and external sources. To establish a single source of truth, The University of Kansas Hospital deployed an enterprise data warehouse (EDW). However, they quickly realized that without an effective data governance program clinicians and operational leaders would not trust the data. Led by senior leadership commitment, The University of Kansas Hospital established processes to define data, assign data ownership and identify and resolve data quality issues. They also have 70+ standardized enterprise data definition approvals planned for completion in the first year and have created a multi-year data governance roadmap to ensure a sustained focus on data quality and accessibility.
Improving Healthcare Performance through Analytics and Cultural Transformation: One Healthcare Organization’s Journey
OSF HealthCare, a pioneer accountable care organization (ACO), was looking to deliver superior clinical outcomes, improve the patient experience, and enhance the affordability and sustainability of its services. OSF’s leaders recognized that to effectively achieve these goals, they needed to reinvent the organization’s performance improvement measurement and reporting system. In addition to deploying new analytics technology, OSF knew they needed to drive a cultural shift throughout the organization to embrace a data-empowered system. By engaging leadership, aligning the initiative with business strategies, and building data-driven clinical and operational improvement teams, OSF was able to save $9-12 million over three years—through both process improvement and cost avoidance. OSF also drove clinical performance improvements in key areas including heart failure and palliative care.
Healthcare executives rely increasingly on executive healthcare dashboards to provide a snapshot of their organization’s performance measured against established monthly and yearly key process indicator (KPI) targets. However, collecting and aggregating the needed data to create the dashboard can be a very time-intensive process and many organizations are using Excel spreadsheets to “cobble together” these dashboards from a variety of sources. Learn how this organization is leveraging a healthcare enterprise data warehouse (EDW) and analytics technology to automate and improve the dashboarding process.
Integrating EHR data into a healthcare enterprise data warehouse (EDW) can take years, depending on the EDW platform and data model. Crystal Run — a physician-owned medical group in New York with more than 300 physicians in 40 medical specialties — couldn’t wait that long. They need a solution that could integrate their EHR data in a matter of months, not years. Using a late-binding model, Crystal Run was able to integrate their EHR data in just 77 days, with easy-to-use tools for data acquisition and storage and metadata management.
Cesarean deliveries have become one of the most common surgical procedures performed in the United States each year. Between 1998 and 2008, the rate of cesarean delivery in the United States rose by 50 percent — from 22-33 percent of all births. Many healthcare stakeholders have turned their attention to reducing this rate for clinical, financial and regulatory reasons. Read how this healthcare system developed a Women and Newborn’s population health registry and discovered they had to start first with addressing their healthcare data quality issues.