Analytics are supposed to provide data-driven solutions, not additional healthcare analytics pitfalls and other related inefficiencies. Yet such issues are quite common. Becoming familiar with potential problems will help health systems avoid them in the future. The three common analytics pitfalls are point solutions, EHRs, and independent data marts located in many different databases. An EDW will counter all three of these problems. The two inefficiencies include report factories and flavor of the month projects. The solution that best overcomes these inefficiencies is a robust deployment system.
Choose by Topic
- Latest Insights
- Accountable Care
- Analyst & IT Roles
- Best Practices
- Big Data
- Business Intelligence
- Care Management and Patient Relationships
- Clinical Analytics and Decision Support
- Dashboards & Reporting
- Data: Quality, Management, Governance
- EMR Fit
- Enterprise Data Warehouse / Data Operating system
- Financial Alignment & ROI
- Health Catalyst Overview
- Health Catalyst University
- Healthcare Analytics Summit
- Healthcare Transformation
- Implementing Health Catalyst Products & Services
- Leadership, Culture, Governance
- Machine Learning / Predictive Analytics
- MACRA / Regulatory Measures
- News Roundup
- NLP & Text Analytics
- Operations and Performance Management
- Outcomes Improvement
- Patient Experience, Engagement, Satisfaction
- Patient Safety
- Payers & Providers
- Physician Engagement
- Population Health
- Precision Medicine
- Quality & Process Improvement
- Value-Based Purchasing / Risk-Based Contracting
Outlined for practical use in the healthcare industry, this eight-level, industry-specific roadmap acts as a guide for organizations striving to be truly data driven. Developed by an independent, cross-industry group, this white paper explains the Analytics Adoption Model, its history and purpose. Organizations can then use the model to determine direction, highlight goals and gauge progress, as well as see the next steps needed to achieve goals associated using data to drive and assess clinical improvements.
Healthcare has remained entrenched in its cottage industry-style of operation, even within huge medical centers and significant medical innovation. The result, as documented by Dr. John Wennberg’s Dartmouth Atlas of Health Care project , is unwarranted variation in the practice of medicine and in the use of medical resources including underuse of effective care, misuse of care, and overuse of care provided to specific patient populations. The root of the problem, Wennberg concludes, is that there is no healthcare “system.” At Health Catalyst, we agree. Healthcare needs to be systematized and standardized in three key areas:1) healthcare analytics or measurement, 2) adoption or how teams and work are organized, and 3) best practice or how evidence/knowledge is gathered, evaluated, and disseminated for adoption.
Analytics - Additional Content
Spend time reading content for you
Every hospital and health system has to juggle significant IT needs with a limited budget. In the middle of these demands and possibilities, hospital executives have to prioritize and decide which technology solutions are the most critical to the health of their organization. I call these most critical IT solutions “survival software.” Advanced clinical analytics solutions are the survival software of the near future, as they really hold the key to achieving the triple aim and survive value-based purchasing.
Healthcare data models are the backbone of innovation in healthcare, without which many new technologies may never come to fruition, so it’s important to build models that focus on relevant content and specific use cases. Health Catalyst has been continuously refining its approach to building concise yet adaptive healthcare data models for years. Because of our experience, we’ve learned five key lessons when it comes to building healthcare data models:
- Focus on relevant content.
- Externally validate the model.
- Commit to providing vital documentation.
- Prioritize long-term planning.
- Automate data profiling.
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:
Healthcare organizations seeking to achieve the Quadruple Aim (enhancing patient experience, improving population health, reducing costs, and reducing clinician and staff burnout), will reach their goals by building a rich analytics ecosystem. This environment promotes synergy between technology and highly skilled analysts and relies on full interoperability, allowing people to derive the right knowledge to transform healthcare. Five important parts make up the healthcare analytics ecosystem:
- Must-have tools.
- People and their skills.
- Reactive, descriptive, and prescriptive analytics.
- Matching technical skills to analytics work streams.
Based on 25 years of healthcare IT experience, Dale outlines a detailed set of criteria for evaluating clinical analytic vendors. These criteria include 1) completeness of vision, 2) culture and values of senior leadership, 3) ability to execute, 4) technology adaptability and supportability, 5) total cost of ownership, 6) company viability, and 7) nine elements of technical specificity including data modeling, master data management, metadata, white space data, visualization, security, ETL, performance and utilization metrics, hardware and software infrastructure.
Chilmark’s 2017 Healthcare Analytics Market Trends Report is a trove of insights to the analytics solutions driving the management of population health and the transition to new reimbursement models. The report reviews the analytics market forces at work, such as:
- The need to optimize revenue under diverse payment models.
- The increasing importance of analytics in general, and a platform in specific, that can aggregate all data.
- Continuing confusion about how to react to MIPS and APMs.
- The growing importance of providing a comprehensive set of open and standard APIs.
- The need for better tools to create analytics-ready data stores.
Healthcare organizations rely on data to support informed decisions. To be truly valuable, data must be high quality and meet two criteria for end-users:
- Data must be transformed from its raw, obscure form into actionable insights.
- Data-driven insights must be immediately accessible at the point of care (versus in static dashboards or buried on the intranet).
Given the fact that up to 80 percent of clinical data is stored in unstructured text, healthcare organizations need to harness the power of text analytics. But, surprisingly, less than five percent of health systems use it due to resource limitations and the complexity of text analytics. But given the industry’s necessity to use text analytics to create precise patient registries, enhance their understanding of high-risk patient populations, and improve outcomes, this executive report explains why systems must start using it—and explains how to get started. Health systems can start using text analytics to improve outcomes by focusing on four key components:
- Optimize text search (display, medical terminologies, and context).
- Enhance context and extract values with an NLP pipeline.
- Always validate the algorithm.
- Focus on interoperability and integration using a Late-Binding approach.
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
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
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.
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.
Analysts are most effective when they have the right tools. In healthcare, that means providing data analysts with a means of accessing and testing ALL of the available data and using it to discover more insights. To do this, analysts need guidance more than they need a detailed set of instructions. And, equally as important, they need a data warehouse and access to a testing environment and data discovery tools, so they can truly do the work they were hired to do: analyze.
We hand-picked the most interesting, useful, credible factoids from 2015 (including the plethora of facts that came out of the 2nd Healthcare Analytics Summit) to create an easy-to-share presentation. The 32 factoids included in this presentation revealed several interesting healthcare trends:
- Trend #1: Healthcare analytics continue to improve outcomes and save money. For example, OSF’s predictive readmission model reduced its all-cause readmission rate to less than 10%.
- Trend #2: New technologies are improving patient engagement. For example, 73 percent of health executives surveyed see positive ROI from personalization technologies, and 76 percent of doctors say patient use of wearable health devices improves engagement.
- Trend #3: Patients and providers agree on data is useful but have security and interoperability concerns. For example, 83 percent of patients don’t trust EHR safety and security, and 83 percent of physicians are frustrated by EHR interoperability.
Improving Patient Safety and Quality through Culture, Clinical Analytics, Evidence-Based Practices, and Adoption
According to the Centers of Disease Control (CDC), an estimated 70,000 patients die each year from hospital-associated infections (HAIs): contrast the CDC statistic with the fact that only 35,000 people die each year in the U.S. from motor vehicle accidents. Learn key best practices in patient safety and quality including: patient safety as a team sport, the added challenges of healthcare being the most complex, adaptive system, and how culture, analytics, and content contribute to improve outcomes and lower costs.
Value-based care has remade the healthcare landscape for small hospitals. Many are struggling to compete with the larger, better-funded medical centers in the communities they serve. Embracing data and analytics is no longer a luxury for these organizations if they are to succeed and remain competitive. Data analysis can assist senior leaders in identifying opportunities for improvement while balancing long-term goals with short-term pressures. Incorporating data in to the culture and making it a part of everyday decision making will enable smaller hospitals to not only survive, but thrive in the new era of value-based care.