How can we help you today?

Reducing Opioid Availability with Improved Prescribing Practices

Historical approaches to the use of opioids in pain management have been associated with overprescribing and have inadvertently contributed to the opioid abuse crisis. Optimizing the use of opioids can help reduce the number of excess pills circulating in the community.

Allina Health, a not-for-profit health system serving Minnesota and western Wisconsin, achieved previous success in reducing opioid prescriptions in outpatient settings through the adoption of standard practices. Though Allina Health had initial success with its opioid prescription reduction efforts, providers still lacked visibility into prescribing practices, leading to variability that made further sustainable improvements challenging. With the help of analytics, Allina Health leveraged its data to develop prescription standards aimed at reducing the oversupply of opioids in the community, while still effectively managing patients’ acute pain after procedures.

Results:

• 15,730 fewer opioid pills prescribed at discharge in one year.
• 16 percent relative reductionin the number of opioid pills prescribed per patient.
• 95 percent of patients that delivered a baby via cesarean section and received opioids at discharge received fewer than 30 opioid pills.

Analytics Improves Insight into PMPM, Reduces Liabilities in Rate-Setting Agreements

In the U.S., Medicaid provides health coverage to more than 68 million low-income men, women, and children, and is funded jointly by states and the federal government. Growing at an unsustainable rate, Medicaid programs have left many states with the challenge of finding new ways to create fiscally stable systems of care that also improve health outcomes.

Oregon established an accountable care model unique to the state composed of coordinated care organizations (CCOs) which are local organizations charged with managing care for members of the Oregon Health Plan—Oregon’s Medicaid program—in addition to finding innovative ways to meet the goals of the Triple Aim: better care, smarter spending, and healthier people. Like all CCOs, Health Share of Oregon required accurate and timely data to support forecasting for rate-setting to remain financially solvent and limit liability in this innovative model. Health Share leveraged analytics to obtain a holistic evaluation of the drivers of per member per month (PMPM) payment performance. Through improved access to this strategic and timely data, Health Share has successfully minimized liability, improved the accuracy of rate-setting utilization data, and reduced analyst time spent compiling complex regulatory reports.

Results:

• Timeliness of rate-setting utilization data improved from two years to just a few months.
• Identified opportunities to effectively reduce liabilities, helping to ensure ongoing financial viability of the organization.
• Rapid integration of new member cost data.

Machine Learning Automates Outpatient Coding

Accurate service line reporting is necessary for a healthcare organization to understand its total cost of care. Organizations that do not understand the total cost of care cannot be successful in risk-sharing and other forms of value-based payment, resulting in a loss of reimbursement.

In an effort to reduce costs, MultiCare Health System, an integrated delivery system serving Washington, decided to outsource all encounter coding, which eliminated the coding of outpatient encounters, negatively impacting service line reporting. To ensure accurate reporting, MultiCare asked its coders to assign an MS DRG code to all hospital-based outpatient encounters, which brought significant additional costs. To mitigate this, MultiCare utilized data analytics and machine learning to develop an algorithm that predicts the MS DRG code for hospital-based outpatient encounters.

By employing machine learning, MultiCare has achieved impressive results, including:

• Successfully restoring service line reporting, enabling the organization to better understand the total cost of care, and supporting future participation in value-based care and risk-sharing agreements.
• Ability to avoid additional labor costs that would be required to perform dual coding, saving more than $1M annually.

Analytics Drive Lean Processes to Lower Healthcare-associated Infections

Healthcare-associated infections (HAIs) remain one of the greatest risks patients face while hospitalized. Each day, about one in 25 hospital patients has at least one HAI—with an estimated 722,000 HAIs in U.S. acute care hospitals annually. Approximately 75,000 of the patients with HAIs died during their hospitalization.

The University of Kansas Health System, a large academic medical system with more than 80 locations across two states, experienced organizational central-line associated bloodstream infections (CLABSI) and catheter-associated urinary tract infection (CAUTI) rates that were higher than desired. A lack of consistent uniform evidence-based maintenance of indwelling urinary catheters and central lines led to unintended care variations, which is a challenge to large healthcare organizations.

Developing a reliable system for preventing CAUTI and CLABSI that produced consistent and accurate results would assist The University of Kansas Health System in HAI prevention. To create this solution, the health system chose to implement lean management for addressing both technical and adaptive work, applying data and analytics from its analytics platform to make improvements driven by lean methodologies. These efforts were initiated within a model cell unit resulting in:

• Only one CAUTI in 1,861 days. Zero CAUTI in 747 days.
• Only one CLABSI in 824 days. Zero CLABSI in 332 days.
• 95^th percentile patient satisfaction ranking.

Improving Screening for Lung Cancer Enables Early Detection

With one of every four deaths in the U.S. being attributed to cancer, it is the second leading cause of death, surpassed only by heart disease. There are more deaths from lung cancer than from any other type of cancer accounting for more than 155,000 deaths annually.

While new lung cancer screening guidelines were available, few providers were compliant with the guidelines, or fully understood the complex reimbursement requirements, particularly the patient characteristics that qualify a patient to be eligible for low-dose computed tomography (LDCT) screening and the documentation required for reimbursement.

Mission Health, based in Asheville, North Carolina, is the state’s sixth largest health system with six hospitals and numerous outpatient and surgery centers. The organization wanted to increase the number of patients screened for lung cancer to catch the disease at an earlier, more treatable phase. Mission established a care process model improvement team, enhanced its screening program, and utilized its analytics platform to extract and integrate data from various source systems to evaluate the impact of LDCT screening and outcomes for its patients. Results from the enhanced program include:

• 71 percent relative increase in LDCT screening for people at increased risk for lung cancer.
• 56 people with lung cancer identified through early screening.
• 4.3 percent relative increase in people being diagnosed at early stage I or II lung cancer.
• 21.2 percent relative reduction in people diagnosed with late stage III or IV lung cancer.

Artificial Intelligence Improves Accuracy of Heart Failure Readmission Risk Predictions

A global pandemic, heart failure (HF) affects at least 26 million people worldwide, and its prevalence only continues to increase. Within the U.S. alone, 5.7 million adults live with HF, carrying a cost of nearly $30.7 billion each year. At 55 percent, HF represents the most common cause of Medicare readmissions, and HF accounts for 42 percent of total admissions for Medicare patients.

Readmissions for HF carry a heavy cost for patients and health systems, in addition to reimbursement penalties from CMS. This makes properly assessing the risk for readmission for patients with HF a top priority. MultiCare Health System leveraged artificial intelligence and machine learning to improve the accuracy of readmission risk predictions for patients with HF. Providing a more accurate risk score in a timely fashion gives care teams more time to intervene effectively and prevent avoidable readmissions.

Results: 

• 85 percent estimated accuracy for heart failure readmission risk predictor. (LACE accuracy around 62 percent)
• Three-fold increase in the number of HF readmission risk-predictions made each day.

Widespread Analytics Adoption Improves ACO Measure Performance

On an annual basis, Accountable Care Organizations (ACOs) are required to accurately report data that is used to assess quality performance. This is necessary in order for the ACO to be eligible to share in any savings generated. Improvements in measure performance are often linked with ACOs that have offered providers the skills, tools, and data required to understand and track their own performance, as well as that of their peers.

Mission Health, based in Asheville, North Carolina, is the state’s sixth-largest health system, spanning the 18 counties of western North Carolina. Mission formed one of the largest ACOs in the country, Mission Health Partners (MHP), providing services for nearly 90,000 patients. While MHP had previously achieved success in improving its ACO measure performance, it sought to increase its quality scores even higher. Without access to transparent, actionable data, leadership was unsure if improvements would be sustained, let alone if existing workflows could lead to new improvements. After developing a comprehensive plan that included a massive expansion to data access, Mission practices were able to sustain initial improvements, identify new opportunities, and improve population health quality even further.

Substantial improvement across multiple ACO measures:

• 29 percent relative improvement in the number of patients receiving colorectal cancer screening.
• 10 percent relative improvement in the number of patients receiving breast cancer screening.
• 7 percent relative improvement in the number of patients with blood pressure under control.

Integrated Data Enables Single Source of Truth and Rapid Adoption

Many healthcare organizations struggle to deliver seamless reporting, advanced visualizations, and end-user self-service models, but these types of analytics are critical to business intelligence and have become a practical and strategic necessity.  There is a lack of trust in data because it can be difficult to access and combine information that is fragmented, coming from multiple, disparate sources such as EMRs, billing, claims, and financial systems. Without an integrated source of clinical and business data in a trusted single source of truth, it is difficult, if not impossible to create a data-driven approach to decision making.

Orlando Health, one of Florida’s most comprehensive private, not-for-profit healthcare networks consisting of eight hospitals and 50 clinics, began its journey to integrate clinical and business data into a single source of truth across the organization when it made the transition from a legacy data warehouse solution that employed an enterprise data model to the Health Catalyst analytics platform, and subsequently to the Health Catalyst^® Data Operating System (DOS™) platform.

Integrated data and ability to deliver superior solutions has resulted in a single source of truth, leading to increased adoption. Once customers realized the timeliness, ease of access, and quality of the improved analytics and visualizations available to them, demand and adoption increased and continues to grow.

• 6,120 queries of the analytics platform each month.
• Users access analytic applications and visualizations more than 700 times each month.

Integrated Healthcare Data Quickly Enables Adaptive, Purpose Driven Analytics

Changes in payment models are putting pressure on clinicians to close gaps in care. To do this, they need instant access to actionable information about their patients and their own performance. However, many electronic health records and business intelligence systems are still grappling with how to deliver the insights necessary to revolutionize the way providers work.

Orlando Health, a Florida-based, not-for-profit health system made up of eight hospitals and 50 clinics, found its enterprise data model difficult to scale, making it challenging to gain insights from its healthcare data. Building upon its analytics platform, Orlando Health recognized the value of immediate access to adaptive, integrated healthcare data that could be rapidly deployed in consumable, actionable visualizations to address a wide spectrum of business needs and use cases, and embraced a next-generation data model.

Results:

• Ten data sources loaded into the platform in under six months.
• As little as one week to deploy dashboards, visualizations, and analytic insights.
• 95 percent reduction in work hours required to incorporate system enhancements.
• 88 days saved in the amount of time required to implement system enhancements.

Improving Transitions of Care for Patients with Pneumonia

Nationally, the readmission rate for patients over age 65 with pneumonia is 15.8 percent. Though not all hospital readmissions are preventable, high readmission rates may reflect performance on care quality, effectiveness of discharge instructions, and smooth transitioning of patients to their home or other setting.

Piedmont Healthcare wanted to standardize pneumonia care across its entire system but lacked the data it needed to identify patients who could benefit from additional transition support. Piedmont convened a care management steering committee and deployed analytics tools to generate actionable data for appropriate and effective transitions of care for its Medicare patients with pneumonia. In less than one year, it reduced its readmission rate for patients with pneumonia by 26 percent.