Academic medical centers (AMCs) are a triple threat on the healthcare court with their combined medical center, education, and research sections. With a unique set of resources, AMCs have the ability to take a comprehensive, holistic approach to patient care. However, one of the challenges they still face is utilizing healthcare analytics effectively within the patient care setting. With the Healthcare Analytics Adoption Model and other data expertise, AMCs can learn how to merge siloed data, while improving operations, and delivering the highest quality of care to each patient.
Enterprise Data Warehouse / Data Operating system
Agnostic Analytics Solutions vs. EHRs: Six Reasons EHRs Can’t Deliver True Healthcare Interoperability
As enterprisewide analytics demands grow across healthcare, health systems that rely on EHRs from major vendors are hitting limitations in their analytics capabilities. EHR vendors have responded with custom and point-solution tools, but these tend to generate more complications (e.g., multiple data stores and disjointed solutions) than analytics interoperability.
To get value out of existing EHRs while also evolving towards more mature analytics, health systems must partner with an analytics vendor that provides an enterprise data management and analytics platform as well as deep improvement implementation experience. Vendor tools and expertise will help organizations leverage their EHRs to meet population health management and value-based payment goals, as well as pursue some of today’s top healthcare strategic goals:
When health system clinicians make care decisions based on their organization’s EHR data alone, they’re only using a small portion of patient health information. Additional data sources—such as health information exchanges (HIEs) and patient-generated and -reported data—round out the full picture of an individual’s health and healthcare needs. This comprehensive insight enables critical, and sometimes life-saving, treatment and health management choices.
To leverage the data from beyond the four walls of a health system and combine it with clinical, financial, and operational EHR data, organizations need an interoperable platform approach to health data. The Health Catalyst® Data Operating System (DOS™), for example, combines, manages, and leverages disparate forms of health data for a complete view of the patient and more accurate insights into the best care decisions.
While many industries are leveraging digital transformation to accelerate their productivity and quality, healthcare ranks among the least digitized sectors. Healthcare data is largely incomplete when it comes to fully representing a patient’s health and doesn’t adequately support diagnoses and treatment, risk prediction, and long-term health care plans. But even with the obvious urgency for increased healthcare digitization, the industry must raise this trajectory with sensitivity to the impacts on clinicians and patients. The right digital strategy will not only aim for more comprehensive information on patient health, but also leverage data to empower and engage the people involved.
Health systems can follow five guidelines to digitize in a sustainable, impactful way:
Achieve and maintain clinician and patient engagement.
Adopt a modern commercial digital platform.
Digitize the assets (the patients) and the processes.
Understand the importance of data to drive AI insights.
Prioritize data volume.
Most healthcare systems have been building, improving, and maintaining proprietary healthcare analytics platforms since the early 2000s and have invested heavily in the people and resources required to do so. As the demands of today’s healthcare environment continue to increase, it’s becoming more difficult for analytic teams to keep up.
This article deals with the six biggest problems to maintaining a homegrown healthcare analytic platform today:
Inability to keep pace with analytic demands.
Difficult to support and scale for the future.
Difficulty finding and keeping talent.
Use of point solutions to fill gaps.
Analytic teams must also support third-party vendors and affiliated groups.
Difficulty keeping abreast of rapidly changing regulatory requirements.
Twenty years after Intermountain Healthcare launched its enterprise data warehouse in 1998, industry leaders are looking at what they did right, what they’d do differently, and what the future holds for healthcare data and analytics. While early successes (such as a hiring framework of social, domain, and technical skills; lightweight data governance; and late-binding architecture) continue to hold their value, advanced analytics and technology and innovation in diagnosis and treatment are reshaping the capabilities of and demands on the healthcare data warehouse. Present-day and future healthcare IT leaders will have to revisit approaches to data warehousing people, processes, and technology to understand how they can improve, continue to adapt, and fully leverage emerging opportunities.
The Homegrown Versus Commercial Digital Health Platform: Scalability and Other Reasons to Go with a Commercial Solution
Public cloud offerings are making homegrown digital platforms look easier and more affordable to health system CTOs and CIOs. Initial architecture and cost, however, may be the only real benefit of a do-it-yourself approach. These homegrown systems can’t scale at the level of commercial vendor systems when it comes to long-term performance and expense, leaving organizations with a potentially costly and undereffective platform for years to come.
Over his 25 years as a health system CIO, Dale Sanders, President of Technology for Health Catalyst, has observed both the tremendous value of healthcare-specific vendor platforms, as well as the shortcomings of homegrown solutions. He shares his insights in a question-and-answer session that addresses pressing issues in today’s digital healthcare market.
Most health systems suffer from data clutter and efficiency problems. As a result, analysts spend most of their time searching for data, not performing high value work. There are three steps that can help you address your data management issues: 1) find all your dispersed analysts in the organization, 2) assess your analytics risks and challenges, 3) champion the creation of an EDW as the foundation for clinical data management.
Smartphone applications, home monitoring equipment, genomic sequencing, and social determinants of health are adding significantly to the scope of healthcare data, creating new challenges for health systems in data management and storage. Traditional on-premises data warehouses, however, don’t have the capacity or capabilities to support this new era of bigger healthcare data.
Organizations must add more secure, scalable, elastic, and analytically agile cloud-based, open-platform data solutions that leverage analytics as a service (AaaS). Moving toward cloud hosting will help health systems avoid the five common challenges of on-premises data warehouses:
Predicting future demand is difficult.
Infrastructure scaling is lumpy and inelastic.
Security risk mitigation is a major investment.
Data architectures limit flexibility and are resource intensive.
Analytics expertise is misallocated.
Looking for a way to share his extensive experience with data warehousing in healthcare, in 2002 Dale Sanders wrote what many consider to be the “EDW Bible.” It’s a document with guidance that, if followed, will drive value and utilization from a data warehouse. We’ve made that report available now.
What are the differences between a database and a data warehouse?
A database is any collection of data organized for storage, accessibility, and retrieval.
A data warehouse is a type of database the integrates copies of transaction data from disparate source systems and provisions them for analytical use.
The important distinction is that data warehouses are designed to handle analytics required for improving quality and costs in the new healthcare environment. A transactional database, like an EHR, doesn’t lend itself to analytics.
Episode Analytics Now Mission Critical as Outcomes Meet Incomes: Partners HealthCare Paves Volume-To-Value Path With Late-Binding Data Warehouse
In this reprint from Microsoft, Dennis Schmuland, MD, FAAFP (Chief Health Strategy Officer, Microsoft US Health & Life Sciences), sits down with Sree Chaguturu, MD (Vice President and Chief Population Health Officer, Partners HealthCare) to learn how Partners HealthCare has prepared for the tipping point of value-based care.
Want to know the best healthcare data warehouse for your organization? You’ll need to start first by modeling the data, because the data model used to build your healthcare enterprise data warehouse (EDW) will have a significant effect on both the time-to-value and the adaptability of your system going forward. Each of the models I describe below bind data at different times in the design process, some earlier, some later. As you’ll see, we believe that binding data later is better. The three approaches are 1) the enterprise data model, 2) the independent data model, and 3) the Health Catalyst Late-Binding™ approach.
I am one of the brave souls who takes the time to read the report issued each spring by the Medicare Payment Advisory Commission (Medpac). The report shows the numbers of Medicare beneficiaries and claims are growing; healthcare organizations are increasingly losing money on Medicare; payment increases certainly will not keep pace with declining margins; and Medicare policies will continue to incentivize quality and push providers to assume more risk. But the report also reveals that some healthcare organizations—referred to as “relatively efficient”—are making money from Medicare with an average 2 percent margin. How do you become one of these organizations? And how do you target and counter Medicare trends that impact your business?
The Data Operating System (DOS™) is a vast data and analytics ecosystem whose laser focus is to rapidly and efficiently improve outcomes across every healthcare domain. DOS is a cornerstone in the foundation for building the future of healthcare analytics. This white paper from Imran Qureshi details the seven capabilities of DOS that combine to unlock data for healthcare improvement:
These seven components will reveal how DOS is a data-first system that can extract value from healthcare data and allow leadership and analytics teams to fully develop the insights necessary for health system transformation.
Using a supermarket analogy, this article helps healthcare leaders understand what data lakes are (open reservoirs for vast amounts of data), why they’re essential (they reduce the time and resources required to map data), and how they integrate with three common analytic architectures:
Early-Binding Data Warehouse
Late-Binding Data Warehouse
Map-Reduce Hadoop System
Data lakes are useful parts of all three platforms, but deciding which platform to integrate a data lake with depends heavily on a health system’s resources and infrastructure.
Once understood and appropriately integrated with the optimal analytics platform, data lakes save health systems time, money, and resources by adding structure to data only as use cases arise.
What do health systems risk when they hold onto an older enterprise data warehouse (EDW) perspective? By thinking about the EDW as a tool for only historic data that’s not highly reliable and can’t support important decisions, organizations miss out on near real-time (NRT) reporting and valuable decision-making resources.
Far from an outdated tool, today’s EDW is capable of meeting rising demands for timely, quality data. Health systems can ensure their EDW reaches its full potential by prioritizing it among their technology and properly supporting it—with the best equipment and human resources. The well maintained EDW is not stuck in the past, but rather, an invaluable tool to move healthcare analytics forward.
Starting and sustaining an enterprise data warehouse (EDW) for a sizeable healthcare organization might seem as challenging as, say, forming a new country. While it is an arduous undertaking, there are plenty who have gone before. In this article, one EDW operations manager shares five steps for success:
Start with a Leadership Commitment to Outcomes Improvement
Build the Right Team
Establish Effective Partnerships with IT
Develop Interest and Gain Buy-In
Pivot Toward Maintaining Success
Successfully implementing and sustaining EDW operations is about establishing and managing priorities and understanding the enterprise-wide implications.
What most often restricts IT innovation at a healthcare organization? It’s not limitations of the tools for innovation (the data infrastructure) or the workforce, but the organizational culture of the health system. A culture that’s too focused on past failed initiatives and their consequences won’t identify opportunities that lead to new ideas. They likely have the right parts for a great idea, but aren’t enabling those parts for innovation.
Organizations can build and environment that fosters innovation in healthcare IT by operating with three principles:
Give teams the freedom to fail.
Remember the adjacent possible.
Leverage organizational networks.
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:
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.
Health systems that leverage healthcare data warehouses position themselves to do more than just survive the transition to value-based care; they empower themselves to achieve and sustain long-term outcomes improvement by enabling data-driven decision making based on high quality data.
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
This executive report starts by examining the origin of EHRs and EDWs, then dives into the value derived from both in terms of their contributions to the major issues impacting healthcare delivery today.
As vice president of technology for a healthcare IT company, I’m often asked what should be considered when selecting a solution for healthcare analytics. Healthcare organizations have many choices when selecting a healthcare data warehouse and analytics platforms. I advise them to consider the following fundamental criteria: 1) time-to-value (measured in months, not years), 2) experience as a predictor of future success, and 3) extensibility to meet your needs.
Which is a faster data-warehousing model, early-binding or late-binding? Skipping the suspense, the late-binding approach is the speedier option. Binding has to do with how data is modeled within the EDW. Early-binding requires business rules to be set up early in the analysis process. This means early-binding isn’t very flexible or adaptable to changes. On the other hand, the late-binding approach is all about speed and flexibility. Business rule decisions can happen at the last moment, right when the analysis takes place.
The data lake style of a data warehouse architecture is a flexible alternative to a traditional data warehouse. It allows for unstructured data. When a warehousing approach requires that the data be in a structured format, there are constraints on the analyses that can be performed because not all of the data can be structured early. The data lake concept is very similar to our Late-Binding approach in that data lakes are our source marts. We increase the efficiency and effectiveness of these through: 1. Metadata, 2. Source Mart Designer, and 3. Subject Area Mart Designer.