Ineffective communication between care providers is a major problem. According to the Joint Commission, 80 percent of serious medical errors involve miscommunication between caregivers during the transfer of patients. Care management teams need to place emphasis on good communication to effectively coordinate care and improve health outcomes. This point is illustrated by Keisha’s story, a patient who had a severe heart attack just two days after her catheterization was postponed due to incomplete information and miscommunication between her PCP, cardiologist, and nurse care manager.
Choose by Topic
When it comes to maximizing analytics ROI in a healthcare organization, the more domains, the merrier. Texas Children’s Hospital started their outcomes improvement journey by using an EDW and analytics to improve a single process of care. It quickly realized the potential for more savings and improvement by applying analytics to additional domains, including:
- Analytics efficiencies
- Organization-wide clinical improvement
A mission-driven culture is a must-have in today’s rapidly changing healthcare environment. Culture is a vital component of a successful organization, as it builds an engaged and committed workforce that’s capable of adapting to shifting demands. Four principles form the basis of a mission-driven culture:
- Engage life-long learners and great listeners.
- Assume positive intent.
- Avoid entitlement.
- Aim for long-term commitment.
The healthcare industry is increasingly focusing on care management, and it shows—patients with serious illnesses and injuries are experiencing better outcomes and living longer. But more needs to be done, as demonstrated by Carlos, the patient in this article who was headed toward invasive, expensive care because he had trouble being compliant with his diabetes plan. Care must be coordinated across the continuum, and tailored to the patient. The role of care management is expanding and can become more effective than ever.
The 21st Century Cures Act, approved by the U.S. Senate on December 7, 2016, is perhaps the most significant federal legislation as it relates to health information technology (HIT) in years. What the Cures Act means for HIT companies and providers is two key things:
- Health information interoperability will be strongly promoted (involves the development of a “trusted exchange framework” which is expected to facilitate the exchange of health information nationally and locally).
- Information blocking practices will be strongly prohibited (e.g., Implementing HIT in nonstandard ways likely to increase the complexity or burden of accessing, exchanging, or using electronic health information—with fines as much as $1,000,000).
Healthcare data is positioned for momentous growth as it approaches the parameters of big data. While more data can translate into more informed medical decisions, our ability to leverage this mounting knowledge is only as strong as our data strategy. Hadoop offers the capacity and versatility to meet growing data demands and turn information into actionable insight. Specific use cases where Hadoop adds value data strategy include:
- Machine learning
There’s a new way to think about healthcare data analysts. Give them the responsibilities of a data detective. If ever there were a Sherlock Holmes of healthcare analytics, it’s the analyst who thinks like a detective. Part scientist, part bloodhound, part magician, the healthcare data detective thrives on discovery, extracting pearls of insight where others have previously returned emptyhanded. This valuable role comprises critical thinkers, story engineers, and sleuths who look at healthcare data in a different way. Three attributes define the data detective:
- They are inquisitive and relentless with their questions.
- They let the data inform.
- They drive to the heart of what matters.
Most health systems struggle to succeed in care management. Whether it’s the frustrating, manual, fragmented processes or the ubiquitous lack of standardization in care management, health systems aren’t alone when it comes to the six care management challenges they struggle to overcome:
- Limited data access.
- Poor data quality.
- Limited involvement in IT and data governance.
- Lack of standardization.
- Limited visibility and transparency for program evaluation.
Before the introduction of healthcare.ai, an open source, healthcare-specific machine learning software, only a small subset of healthcare staff (primarily data scientists) had the ability to leverage predictive analytics to improve outcomes. Healthcare.ai will democratize machine learning by empowering everyone in healthcare with the appropriate technical skills (BI developers, project managers, data architects, etc.) to download the healthcare.ai tools (packages for R and Python), request features, ask questions, and contribute code. What sets healthcare.ai apart from other machine learning tools is its healthcare-specific functionality:
- Pays attention to longitudinal questions.
- Offers an easy way to do risk-adjusted comparisons.
- Provides easy connections and deployment to databases.
Care management is an important field in healthcare that ensures cost-effective, timely, and personalized care. Essentially, it gets the right care to the right patients at the right time. An effective care management system is defined by three components:
- The fundamental of patient-centered care: understanding each patient’s individual needs, developing relationships with them, and providing tailored care.
- The technology to deliver real-time data and support the workflows and processes of care management teams.
- A culture of continuous improvement integrated throughout the organization. A care management platform must be supported by best practices, analytics, and adoption to lead and sustain outcomes improvement.
Risk stratification is essential to effective population health management. To know which patients require what level of care, a platform for separating patients into high-risk, low-risk, and rising-risk is necessary. Several methods for stratifying a population by risk include: Hierarchical Condition Categories (HCCs), Adjusted Clinical Groups (ACG), Elder Risk Assessment (ERA), Chronic Comorbidity Count (CCC), Minnesota Tiering, and Charlson Comorbidity Measure. At Health Catalyst, we use an analytics application called the Risk Model Analyzer to stratify patients into risk categories. This becomes a powerful tool for filtering populations to find higher-risk patients.
Patients with complex care needs, like Arline in this real-life story, account for the highest percentage of costs. Yet, they aren’t necessarily receiving the best care. A care management program for these patients can make all the difference by helping patients and caregivers more effectively manage their health conditions. It takes time, effort, and the implementation of new care delivery models and support systems to realize those benefits, however.
A big key to improving quality and patient care is engaging physicians and nurses. As many healthcare systems begin to implement improvement initiatives, they must ensure their clinicians are supportive and engaged in order to achieve success. Senior-level executives need to understand the challenges their clinical staff are facing in feeling overwhelmed, having too little time, as well as not really understanding new risk-based payment models. Knowing what motivates physicians and nurses to engage (and what doesn’t) ensures process improvements become tangible, sustainable, while at the same time building trust between clinicians and the healthcare organization.
Health systems are faced with the challenge of doing more than just reducing costs and improving quality of care—they must maximize their Return on Engagement by identifying and working with the patients they’ll impact the most. Health Catalyst’s Care Management Suite promises to help systems identify and improve the outcomes for these patients by delivering a comprehensive population health approach that addresses the five critical parts of any successful care management program:
- Data Integration
- Patient Stratification and Intake
- Care Coordination
- Patient Engagement
- Performance Measurement
Evidence-based medicine is an important model of care because it offers health systems a way to achieve the goals of the Triple Aim. It also offers health systems an opportunity to thrive in this era of value-based care. In specific, there are five reasons the industry is interested in the practice of evidence-based medicine: (1) With the explosion of scientific knowledge being published, it’s difficult for clinicians to stay current on the latest best practices. (2) Improved technology enables healthcare workers to have better access to data and knowledge. (3) Payers, employers, and patients are driving the need for the industry to show transparency, accountability, and value. (4) There is broad evidence that Americans often do not get the care they need. (5) Evidence-based medicine works. While the practice of evidence-based medicine is growing in popularity, moving an entire organization to a new model of care presents challenges. First, clinicians need to change how they were taught to practice. Second, providers are already busy with increasingly larger and larger workloads. Using a five-step framework, though, enables clinicians to begin to incorporate evidence-based medicine into their practices. The five steps include (1) Asking a clinical question to identify a key problem. (2) Acquiring the best evidence possible. (3) Appraising the evidence and making sure it’s applicable to the population and the question being asked. (4) Applying the evidence to daily clinical practice. (5) Assessing performance.
In an industry known for its complex challenges that can take years to overcome, health systems can leverage healthcare data warehouses to generate seven quick wins—reporting and analytics efficiencies that empower healthcare organizations to thrive in a value-based world:
- Provides significantly faster access to data.
- Improves data-driven decision making.
- Enables a data-driven culture.
- Provides world class report automation.
- Significantly improves data quality and accuracy.
- Provides significantly faster product implementation.
- Improves data categorization and organization.
Patient engagement is critical as we move toward population health—as patients who engage in their own care by following medical recommendations and making healthy nutrition and lifestyle choices will have better outcomes and experiences. There isn’t, however, a clear path to successful patient engagement. Fortunately, public health can lend several established principles that may help us better involve patients in their own care:
- Using systematic, population-level solutions that require less individual effort.
- Engaging patients on interpersonal and community levels as well as personal.
- Identifying root-cause, assessing and capitalizing on strengths, and engaging stakeholders.
- Using strategies from behavioral economics to help individuals make good choices.
- Anticipating failure and learning from it.
There’s a lot at stake for healthcare organizations when it comes to securing data. A primary concern is to protect privacy and avoid costly breaches or leaks, but at the same time, data must be accessible if it’s to be used for actionable insights. This executive report introduces four balancing acts that organizations must maintain to build an ideal data security framework:
- Data de-identification
- Cloud environments
- User access
Healthcare information systems are integral to hospital operations and clinical care for patients. In the 1960s healthcare was driven by Medicare and Medicaid and HIT developed shared hospital accounting systems. In the 1970s communication between departments and individual transactional systems became important. DRGs drove healthcare in the 1980s and HIT needed to find ways to pull both clinical and financial data in order for reimbursements. The 1990s saw competition and consolidation drive technology to create IDN-like integration. In the 2000s outcomes-based reimbursement became the drive behind developing real-time clinical decision support. For the future, ACOs and value-based purchasing means that CIOs will need to implement data warehouses and analytics application to provide the insights to drive performance improvement necessary for hospital survival.
The state of healthcare information technology and analytics has evolved to the point where a revised executive structure is advisable in the C-suite. This new structure calls for a Chief Data Officer (CDO) to focus on extracting data from systems and on mining value from that data, rather than getting data into systems, which is the responsibility of the CIO. This article makes the case for the CDO, explains how the need for this emerging role evolved, outlines its responsibilities, advises on how to recruit and budget for this position, and details its domain in eight critical business areas:
- Governance and standards
- Managing risk
- Reducing costs
- Driving innovation
- Data architecture and technology
- Data analytics
- Meeting regulatory demand
- Creating business value
The Top Seven Analytics-Driven Approaches for Reducing Diagnostic Error and Improving Patient Safety
From a wrong diagnosis to a delayed one, diagnostic error is a growing concern in the industry. Diagnostic error consequences are severe—they are responsible for 17 percent of preventable deaths (according to a Harvard Medical Practice study) and account for the highest portion of total payments (32.5 percent), according to a 1986-2010 analysis of malpractice claims. Patient safety depends heavily on getting the diagnosis right the first time. Health systems know reducing diagnostic error to improve patient safety is a top priority, but knowing where to start is a challenge. Systems can start by implementing the top seven analytics-driven approaches for reducing diagnostic error:
- Use KPA to Target Improvement Areas
- Always Consider Delayed Diagnosis
- Diagnose Earlier Using Data
- Use the Choosing Wisely Initiative as a Guide
- Understand Patient Populations Using Data
- Collaborate with Improvement Teams
- Include Patients and Their Families
Too much is at stake in value-based healthcare and the technology needed to provide it. When it comes to investing in the best healthcare analytics tools for delivering data-driven care management and outcomes improvement, executives should compare these seven points to determine whether an electronic health record or an enterprise data warehouse should be the foundation of their analytics platform:
- Incorporating data from a wide range of sources
- Ease of reporting
- The data mart concept
- Relevance of each to value-based care
- Relevance of each to managing population health
- Surfacing results of sophisticated analysis for physicians at the right time
- Ability to combine best practices, data, and technology tools into a system of improvement
The shift from fee-for-service to value-based reimbursements has good and bad consequences for healthcare. While the shift will ultimately help health systems provide higher quality lower cost care, the transition may be financially disastrous for some. In addition, the shifting revenue mix from commercial payers to Medicare and Medicaid is creating its own set of challenges. There are, however, three keys to surviving the transition: 1) Effectively manage shared savings programs to maximize reimbursement. 2) Improve operating costs. 3) Increase patient volumes. With an analytics foundation, health systems will be able to meet and survive today’s healthcare challenges.
This article examines how to define population health through a review of the top analytics research firms. It lands on a single theme, but in the process it uncovers six common categories of IT capabilities required to successfully manage population health:
- Data Aggregation
- Patient Stratification
- Care Coordination
- Patient Engagement
- Performance Reporting
A key feature of effective analytics infrastructure in healthcare is a metadata-driven architecture. In this article, three best practice scenarios are discussed:
- Automating ETL processes so data analysts have more time to listen and help end users
- Using a metadata repository to enhance data literacy among users and improve trust in data, thus enabling data governance policies
- Improving turnaround time for data analysts who support frontline staff who, in turn, monitor interventions based on evidence-based medicine that is constantly changing