Hospital readmissions can impact the health outcomes for patients and result in costly readmission penalties from CMS. Learn how the data analytics teams at Westchester Medical Center Health Network and network member Bon Secours Charity Health System utilized its analytics platform, in coordination with a machine learning algorithm, to build a knowledgeable and accurate readmission risk model that better reflected its patient population.
In the U.S., 5.7 million adults have heart failure (HF), costing the nation an estimated $30.7 billion each year. Learn how MultiCare leveraged AI and machine learning to more accurately predict the readmission risk for patients with HF.
Improving transitions of care from hospital to home is key to reducing readmissions for patients with pneumonia. Learn how Piedmont Healthcare used data to effectively manage care transitions and reduce readmissions in less than one year.
For healthcare organizations, sustaining improvements that have been adopted in more than one part of an organization remains a serious challenge. Learn how MultiCare has sustained its elective colon surgery improvement efforts while identifying new opportunities.
It is estimated that $25 to $45 billion is spent annually on avoidable complications and unnecessary hospital readmissions—the result of inadequate care coordination and insufficient management of care transitions. By implementing care coordination programs and leveraging its analytics platform, the University of Texas Medical Branch reduced its readmission rate and achieved significant cost avoidance.
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.
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.
Nationally, readmission within 90 days after colorectal surgery occurs in about one in four patients, at a cost of approximately $9,000 per readmission. Committed to improving its clinical and financial outcomes, MultiCare, an integrated healthcare delivery system in the Pacific Northwest, decided to focus an improvement effort on elective colorectal surgery when it recognized that patient population had a high opportunity for improvement in both clinical outcomes and cost.
Effectively using its existing quality improvement methodology and Collaborative structure, MultiCare leveraged the work of the Enhanced Recovery After Surgery (ERAS) Society and identified and implemented standardized best practice care routines and interventions that would benefit this population. By using the information in the Enterprise Data Warehouse and analytics applications to monitor clinical outcomes and compliance, and leveraging technology in the EHR to provide decision support and order sets at the point of care, MultiCare was able to significantly improve the clinical outcomes for these patients.
19 percent reduction in readmission rates.
22 percent reduction in length of stay.
85 percent reduction in infections related to colorectal surgery.
Nationally, hospitalization for persons with mental health disorders has increased faster than hospitalization for any other condition. Of concern is the lack of bed space to intake these patients on a timely basis. In Minnesota, for example, more than 50 percent of available state psychiatric beds were closed between 2005 and 2010. Furthermore, readmission rates for patients with mood disorders is higher than any other mental health condition, with 15 percent readmitted within 30 days of hospital discharge and up to 22.4 percent of patients with schizophrenia being readmitted. While the average cost of a readmission in the U.S. is approximately $7,200, of greater concern is hospital readmission represents poor patient outcomes related to lack of adequate access to community mental health resources and challenges with adherence to care plans needed to prevent chronic relapse.
In response to these challenges, Allina Health put a new care transition process in place, redesigned workflow, and added key patient support roles. To measure the effectiveness of new interventions, Allina relied on the Health Catalyst Analytics Platform, which includes the Late-Binding™ Enterprise Data Warehouse and a broad suite of analytics applications.
27 percent relative reduction in potentially preventable readmission rate.
80 percent patient retention rate in established outpatient mental health services.
Nationally, approximately 700,000 hospitalizations occur each year with the principle diagnosis of Chronic Obstructive Pulmonary Disease (COPD), with one in five patients being readmitted within 30 days. Even with a national cost for each COPD readmission costing between $9,000 and $12,000, evidence-based measures that improve patient outcomes and decrease COPD readmissions are largely lacking.
When reviewing organizational performance for 30-day all cause readmission, MultiCare Health System identified COPD as one of the top two readmission diagnoses, along with a rate higher than expected. This prompted the organization to take action. MultiCare implemented a NOREADMITS bundle, using the Health Catalyst Analytics Platform and integrating performance measures for each element of the bundle, resulting in:
16.5 percent reduction in readmission rate.
Approximately 34 fewer patients with COPD readmitted each year, saving an estimated $360,000 annually based on national benchmarks.
95 percent of COPD patients were assessed for readmission risk.
Two-fold increase in COPD order set utilization.
Healthcare organizations are among the most complex forms of human organization ever attempted to be managed, making transformation a daunting task. Despite the challenges associated with change, Texas Children’s Hospital identified that it needed to evolve into a data-driven outcomes improvement organization.
Texas Children’s embarked on a journey to transform care, building a three-systems approach—analytics, best practice, and adoption—designed to develop a data-driven quality improvement organization that could achieve outcomes improvement expediently and at scale across the entire organization. Texas Children’s leadership knew that the foundation for clinical systems integration would be meaningful, actionable data. That realization prompted the organization to implement the Health Catalyst Analytics Platform including a Late-Binding™ Data Warehouse (EDW) and a broad suite of analytics applications.
After deploying the analytics platform supported by multidisciplinary quality improvement teams, Texas Children’s was able to improve patient outcomes related to the following:
35 percent relative decrease in hospital-acquired conditions (HACs).
44 percent relative decrease in LOS for patients with Diabetic ketoacidosis (DKA).
30.9 percent relative reduction in recurrent DKA admissions per fiscal year.
Since 2004, the US healthcare system has annually ranked last relative to 10 other developed nations in quality, access, efficiency, equity, and health outcomes. In an effort to improve the quality of care and patient outcomes in the U.S., the Center for Medicare and Medicaid (CMS) launched a series of quality incentive programs designed to generate a shift from volume to value-based reimbursement. The health insurance industry soon followed their lead, and started writing contracts with hospitals in which a percentage of payment was based on performance on selected quality metrics.
Faced with the challenge of reporting on numerous incentive programs with differing expectations, Mission Health leveraged their enterprise data warehouse to aggregate the data needed to track the quality measures. With millions of dollars on the line with one particular payer, Mission developed an analytics application to monitor performance on the metrics in that contract. The application was used to analyze whether performance feedback and workflow changes would lead to improved performance on the metrics, thus ensuring that they would maximize reimbursement, while improving care for patients.
Achieved 100 percent of all at risk dollars.
100 percent of the ambulatory metric targets were exceeded, some by as much as 19 percent.
All five hospitals exceeded targets for 80 percent or more of their inpatient metrics.
Diabetes is the most common chronic illness for children living in developed countries. Leaders at Texas Children’s Hospital wanted to take a more data-driven approach to population health management for children with diabetes. They created a Care Process Team (CPT) to pursue outcomes improvements related to diabetic ketoacidosis (DKA) since data from the EDW revealed that 64% of diabetes patients discharged had this life-threatening condition.
After the CPT achieved their initial goal of improving care for patients admitted to the hospital with DKA, they set out to implement larger improvements that would benefit the entire population of diabetes patients.
By empowering CPT members, leveraging data to drive decisions, and implementing new interventions effectively, the Diabetes CPT members have improved population health for patients with diabetes across all settings of care. Below are a few of the most significant results.
44 percent relative decrease in LOS for patients with DKA.
30.9 percent relative reduction in recurrent DKA admissions per fiscal year.
34.4 percent relative improvement in the percentage of patients with diabetes who receive the influenza vaccine.
Post Operative Atrial Fibrillation occurs in up to 30 percent of all patients after cardiac surgery. This serious complication increases the length of the patient’s hospital stay, and is associated with a twofold increase in the incidence of cerebral infarction and an increased risk of 30-day mortality. Timely and consistent management of Post Op Afib can prevent significant complications and help prevent death. To standardize such an approach to managing Post Op Afib, Allina Health’s Minneapolis Heart Institute created a physician committee to raise consensus on and develop a protocol for Post Op Afib management.
The committee ultimately created a nurse-driven protocol and decision support algorithm linked to the health system’s electronic health record (EHR). Additionally, it uses analytics, supported by Health Catalyst’s Late-Binding™ Enterprise Data Warehouse (EDW), to track physician ordering rate, patient outcomes, and cost. This combination of people, processes, and analytics tools has made a significant difference for Allina and its patients.
Two-day reduction in ICU LOS.
5.9 percentage point reduction in ICU readmission rate.
$1.5 million savings.
By the age of 60, more than one-third of women in the United States have had a hysterectomy. Healthcare systems across the country are recognizing that a women’s health service line offers a pathway to improving care and decreasing cost for these patients. Having accurate activity-based costing information is necessary to uncover opportunities for clinical practice improvement and cost reduction.
The University of Pittsburgh Medical Center (UPMC) made the decision to organize Women’s Health as a service line across the entire health system. UPMC fortified this approach with strong and collaborative leadership, an enterprise data warehouse, and an activity-based cost management system. The results:
20 percent reduction in inpatient length of stay for hysterectomies (over a three-year time period)
34 percent reduction in open hysterectomies
28.3 percent reduction in 30-day readmissions for hysterectomies
These results were obtained during a time when this clinical service saw a 25 percent improvement in its contribution margin.
The consequences of poor-quality surgical care are significant for both hospitals and patients. Consider the following: One in four patients having a colon re-section is readmitted within 90 days, costing U.S. healthcare approximately $300 million a year and negatively affecting the lives of tens of thousands of patients and their families.
In 2013, Mission Health, North Carolina’s sixth-largest health system, identified opportunities to improve clinical outcomes for its bowel surgery patients. With a vision of achieving the best outcome for each patient, Mission set goals to reduce length of stay (LOS), decrease readmissions, and reduce surgical site infections (SSIs) for its bowel surgery patients.
Mission recognized that care process models (CPMs) were key to making it easier for clinicians to deliver the best care to patients by doing the right thing consistently. The health system therefore organized a multidisciplinary improvement team charged with developing and implementing an evidence-based CPM for bowel surgery. In support of this effort, Mission leveraged technology and analytics to encourage clinician adoption of the CPM and to deliver performance insights.
Through these efforts, Mission has achieved impressive improvements in bowel surgery care:
92 percent reduction in colorectal surgery SSI rates
28.5 percent reduction in mortality
10.6 percent reduction in 30-day readmissions
4.4 percent reduction in LOS
8.5 percent reduction in cost per case
U.S. hospital stays cost the health system at least $377.5 billion per year. In today’s value-based care environment, hospitals are under increasing pressure to avoid patient harm and maintain quality while also lowering costs. Reducing hospital length of stay (LOS), especially as it relates to avoiding unnecessary hospital-acquired conditions (HACs), is a primary indicator of a hospital’s success in achieving these goals.
El Camino Hospital, a 395-bed multi-specialty community hospital in Mountain View, Calif., places a high priority on keeping patients safe. However, when it came to its goal of reducing LOS, leaders recognized that they faced some major challenges, including:
The complexity of implementing a multi-layered, multi-disciplinary approach to improving the patient discharge process.
Identifying what issues were contributing the most to increased LOS so that they could be addressed.
By implementing analytics and protocols that provide access to actionable data, the LOS reduction team was able to identify patients at high risk for increased LOS so that they could develop and track critical interventions. El Camino’s patient-centered approach to tackling LOS reduction also included multi-disciplinary cooperation, leadership buy-in, and additional resources to enhance discharge care coordination.
This innovative, systematic approach resulted in not only a better than anticipated reduction in ALOS of 7.8 percent, but also:
14.8 percent reduction in readmissions
55 percent reduction in healthcare acquired conditions (HACs)
32 percent reduction in incidence of AHRQ patient safety indicators (PSIs).
$2.2 million projected annual cost savings
People with disabilities face daunting challenges in accessing basic healthcare. As a result, they frequently use hospitals and emergency rooms, and are four times as likely to be hospitalized compared to the general population.
Allina Health has deployed an effective “primary care medical home” model that gives patients with disabilities the care and support they need outside of the hospital setting. Key strategies of the model include assigning dedicated care coordinators to each patient; strengthening care coordination across the continuum of services; and an analytics platform from Health Catalyst to target opportunities for improvements and savings.
Allina’s data-driven efforts to strengthen care of patients with disabilities have made a clear and meaningful impact; most importantly, on patient outcomes. They have achieved: 30% reduction in hospitalizations and 66% reduction in hospitalization days; 79% reduction in 30-day readmissions days; significantly improved access to care; and saved $4.5 million over a one-year period.
With nearly 20 percent of elderly patients released from a hospital being readmitted within 30 days, Allina Health is focused on providing patients optimum care and support post discharge to minimize readmissions. Focusing on 30-day potentially preventable readmissions (PPRs) as its global outcome measurement, Allina Health used key clinical variables to derive the clinical relationships between hospitalizations that determine PPRs. It further built analytic capabilities to identify opportunities for improvement in care management and to test quality improvement ideas.
Allina Health’s multipronged solution included redesigning care management processes, implementing predictive analytics to identify at-risk patients, using analytics to measure the impact of its interventions, and educating patients, families, and clinicians.
These efforts are driving measurable improvements including: 10.3 percent overall reduction in PPRs, 27 percent reduction in PPRs for patients with clinic follow-up within 5 days, and $3.7 million reduction in variable costs due to avoided readmissions.
Disability is one of the United States’ most important public health issues—with approximately 15 percent of citizens affected. Allina Health created The Courage Kenny Rehabilitation Institute (CKRI) to help people with disabilities, injuries, or complex medical conditions achieve the highest possible degree of health, functionality, and quality of life.
CKRI’s advanced model for rehabilitation care focuses on the whole person, one that looks beyond the medical to address vocational, social, and emotional needs. This collaborative model enables comprehensive and seamless care across the continuum while preparing the organization to operate in a value-based, at-risk environment. CKRI also implemented an analytics infrastructure to help focus its resources appropriately and to measure success.
This innovative approach has optimized patients’ quality of life with up to 76 percent reduction in hospitalizations and 53 percent reduction in ED visits – resulting in annual community cost savings of $11.2 M.
MultiCare Health System, an IDS serving communities throughout Washington State, recently undertook an initiative to improve the care of, cost of, and experience for pneumonia patients. This initiative included the building of evidenced-based order sets (and driving their adoption), assigning a team of social workers called “personal health partners” to research and improve patient follow-up and communication, and deploying an analytics application to provide near real-time feedback on compliance and performance while offering a single view of patient-specific data across multiple visits and care settings, such as medication and readmission histories. Through these efforts, MultiCare has realized significant outcome improvements including reducing pneumonia readmissions by 23 percent, a 28 percent reduction in mortality rate, a 2 percent decrease in LOS, and a 6.4 percent reduction in average variable cost per patient.
Achieve Reduced Heart Failure Readmission Rates: One Healthcare Organization’s Care Coordination Strategy
Heart failure (HF) sends more US adults over 65 to the hospital than any other cause—costing Medicare alone more than $17 billion annually—with readmissions significantly contributing to the issue. For large integrated networks like Allina Health, efforts to reduce readmissions for HF patients are challenged by the need for coordinated care and consolidated data across the care continuum. Allina implemented a multidisciplinary HF management program with a nurse care coordinator and nurse practitioners who assure patient engagement and provide a “bridge” between different points in the care continuum. These important people and processes are aided by access to data from an enterprise data warehouse that merges data across the health system and gives providers insight into HF care and performance metrics. The program has helped Allina achieve a 30-day HF readmission rate well below the national average —17 percent in 10 of 11 hospitals doing cardiac care.
MultiCare, an integrated delivery system (IDS) in the Pacific Northwest, has established a Clinically Integrated Network (CIN) to serve as a model for value creation that benefits patients, providers, and payers. However, to create a truly integrated network, MultiCare needed to build a system of collaboratives—multidisciplinary, clinically focused teams charged with developing clinical care standards and pathways and then collaborating with operations to get them implemented across the enterprise—to improve outcomes in a growing range of clinical domains including Critical Care, Women’s, Surgery, Medicine, Cardiac, and Pediatric. The outcomes of this collaborative care include a 65 percent reduction in sepsis mortality rate, a 75 percent reduction in time required to approve system-wide care guidelines, and a significant contribution to a system-wide cost savings trajectory of more than $100 million over the last three years.
An estimated 24 percent of patients who are discharged with heart failure (HF) are readmitted to the hospital within 30 days. Learn how this healthcare organization engaged physicians and multidisciplinary teams to improve their outcomes. Deploying evidence best practices—medication reconciliation, follow-up appointments, follow-up phone calls and teach back—they reduced and sustained their 30-day HF readmission rates by 29 percent, and their 90-day HF readmissions by 14 percent. They have seen their process measures increase significantly: 120 percent increase in follow-up appointments; 78 percent increase in pharmacist medication reconciliation; 87 percent increase in follow-up phone calls; 84 percent increase in teach-back interventions.
The Centers for Medicare & Medicaid Services (CMS) is tying reimbursement to hospital readmissions. Healthcare systems are investigating hospital readmissions reduction programs to improve patient outcomes and avoid CMS penalties. Learn how this healthcare system, determined to improve heart failure care for its patients, increased their documented follow-up appointments by 270 percent.