Equity impacts the fabric of society down to the type and quality of healthcare different racial and ethnic patient populations receive. COVID-19 has underscored disparities in healthcare delivery in the United States, as the pandemic has disproportionately affected the nation’s black communities. To care for and recognize the value of all individuals, healthcare must leverage data and analytics to better understand patient populations by race and ethnicity and determine how to meet the needs of its underserved populations.
Learn more about Health Catalyst Editors
Health Catalyst Editors is a team of senior editors and writers at Health Catalyst that bring over 60+ combined years of healthcare writing experience and a broad knowledge of the industry
Read articles by Health Catalyst Editors
As Health Catalyst continues to engage its health system partners in their COVID-19 journeys through virtual client huddles, topics are delving further into restarting ambulatory care and elective procedures. The May 21, 2020, forum explored how organizations are responding to the pandemic and planning for the next phases. Participants explored two vital topics in the COVID-19 era:
How virtual care analytics supports rapid change in ambulatory care delivery.
How analytic insights help drive a COVID-19 financial recovery plan.
Health systems alike struggle to effectively manage hospital patient flow. With machine learning and predictive models, health systems can improve patient flow for different departments throughout the system like the emergency department. Health systems should focus on three key areas to foster successful data science that will lead to improved hospital patient flow:
Key 1. Build a data science team.
Key 2. Create a ML pipeline to aggregate all data sources.
Key 3. Form a comprehensive leadership team to govern data.
Improving hospital patient flow through predictive models results in reduced patient wait times, reduced staff overtime, improved patient outcomes, and improved patient and clinician satisfaction.
More than 100 attendees joined the first of a series of Health Catalyst virtual client huddles designed to support client partners and aid collaboration and direct client connections in this time of unprecedented change. According to an April 2020 survey of Health Catalyst clients, 72.6 percent said they had a strong interest in examples, guidance, and tools from other health systems. In the client-only session, insights shared included the most common COVID-19 analytic projects and one health system’s elective surgery plan.
The health system shared the challenges they faced in understanding the financial impact of halting elective surgeries as well as creating a plan for working through their backlog. They also shared the tools and strategies they are using to aid their financial recovery.
Effective, sustainable healthcare transformation rests in the organizational operations that power care delivery. Operations include the administrative, financial, legal, and clinical activities that keep health systems running and caring for patients. With operations so critical to care delivery, forward-thinking organizations continuously strive to improve their operational outcomes. Health systems can follow thought leadership that addresses common industry challenges—including waste reduction, obstacles in process change, limited hospital capacity, and complex project management—to inform their operational improvement strategies.
Five top insights address the following aspects of healthcare operational outcomes improvement:
Quality improvement as a foundational business strategy.
Using improvement science for true change.
Increasing hospital capacity without construction.
Leveraging project management techniques.
Features of highly effective improvement projects.
The focus on analytics is contributing to the “EHR problem”—doctors prioritizing the EHR over patients. The Healthcare Analytics Adoption Model (HAAM) walks healthcare organizations through nine levels that lay the framework to fully leverage analytic capabilities to improve patient outcomes:
Level 1. Enterprise Data Operating System
Level 2. Standardized Vocabulary & Patient Registries
Level 3. Automated Internal Reporting
Level 4. Automated External Reporting
Level 5. Waste and Care Variability Reduction
Level 6. Population Health Management & Suggestive Analytics
Level 7. Clinical Risk Intervention & Predictive Analytics
Level 8. Personalized Medicine & Prescriptive Analytics
Level 9. Direct-To-Patient Analytics & Artificial Intelligence
Analytics are crucial to becoming a data-driven organization, but providers and administrators can’t forget about the why behind the data—to improve outcomes. Following the HAAM enables organizations to build a sustainable, analytic platform and empower patients to become data-driven when it comes to their own care.
As value-based care (VBC) definitions and goals continue to shift, organizations struggle to create a roadmap for population health management (PHM) and to track associated costs and revenue. However, health systems can move forward with PHM amid the uncertainty by following the best practices of a path to value:
Begin with Medicare Advantage—a good growth opportunity with low barriers to entry.
Focus on ambulatory, not acute, care as it delivers more value.
Leverage registries based on utilization to identify the most impactable 3 to 10 percent of utilizers.
Simplify the physician burden by focusing on reasonable measures.
Compared to industries such as aerospace and automotive, healthcare lags behind in decision support innovation. Following the aerospace and automotive arenas, healthcare can learn critical lessons about improving its clinical decision support capabilities to help clinicians make more efficient, data-informed decisions:
Achieve widespread digitization: Healthcare must digitize its assets and operations (patient registration, scheduling, encounters, diagnosis, orders, billings, and claims) for effective CDS similarly to how aerospace digitized the aircraft, air traffic control, baggage handling, ticketing, maintenance, and manufacturing.
Build data volume and scope: Healthcare must collect socioeconomic, genomic, patient-reported outcomes, claims data, and more to truly understand the patient at the center of the human health data ecosystem.
With leadership alignment, easy access to data, and a roadmap to reach their objectives, health systems can drastically increase revenue and grow market share by applying four principles:
Key 1. Alignment.
Key 2. Vehicles.
Key 3: Five tools: access to data, data acumen; finance, vision to execution, and prioritizing outcomes.
Key 4: Education.
Access to the right data can drive changes that generate $48M in revenue, surpassing the year three market share goals in year two.
As healthcare organizations strive to provide better care for patients, they must have an effective clinical measurement system to monitor their progress. First, there are only two potential aims when designing a clinical measurement system: measurement for selection or measurement for improvement. Understanding the difference between these two aims, as well as the connection between clinical measurement and improvement, is crucial to designing an effective system.
This article walks through the distinct difference between these two aims as well as how to avoid the common pitfalls that come with clinical measurement. It also discusses how to identify and track the right data elements using a seven-step process.
Health system mergers can promise significant savings for participating organizations. Research, however, indicates as much as a tenfold gap between expectation and reality, with systems looking for a savings of 15 percent but more likely to realize savings around 1.5 percent.
Driving the merger expectation-reality disparity is a complex process that, without diligent preparation and strategy, makes it difficult for organizations to fully leverage cost synergies. With the right framework, however, health systems can achieve the process management, data sharing, and governance structure to align leadership, clinicians, and all stakeholders around merger goals.
After a tumultuous 2019, healthcare organizations are pivoting to make sense of the latest changes and prepare to face the top 2020 healthcare trends:
Consumerism—Can health systems respond to the consumer demands of better access and price transparency?
Financial Performance—With mergers, acquisitions, and private sector companies entering the healthcare arena, how will traditional hospitals and clinics compete?
Social Issues—How will health organizations respond to the opioid crisis and consider social determinants of health as part of the care process to provide comprehensive treatment?
As health systems struggle to survive amidst constant change, they must look forward and proactively prepare for what’s to come in 2020.
Putting Patients Back at the Center of Healthcare: How CMS Measures Prioritize Patient-Centered Outcomes
Today’s healthcare encounters are too often marked by more clinician screen time than patient-clinician engagement. Increasing regulatory reporting burdens are diverting clinician attention from their true priority—the patient. To put patients back at the center of care, CMS introduced its Meaningful Measures framework in 2017. The initiative identifies the highest priorities for quality measurement and improvement, with the goal of aligning measures with CMS strategic goals, including the following:
Empowering patients and clinicians to make decisions about their healthcare.
Supporting innovative approaches to improve quality, safety, accessibility, and affordability.
Health systems rely on data to make informed decisions—but only if that data leads to the right conclusion. Health systems often use common analytic methods to draw the wrong conclusions that lead to wasted resources and worse outcomes for patients. It is crucial for data leaders to lay the right data foundation before applying AI, select the best data visualization tool, and prepare to overcome five common roadblocks with AI in healthcare:
Predictive Analysis Before Diagnostic Analysis Leads to Correlation but Not Causation.
Change Management Isn’t Considered Part of the Process.
The Wrong Terms to Describe the Work.
Trying to Compensate for Low Data Literacy Resulting in Unclear Conclusions.
Lack of Agreement on Definitions Causes Confusion.
As AI provides more efficiency and power in healthcare, organizations still need a collaborative approach, deep understanding of data processes, and strong leadership to effect real change.
While many healthcare organizations have implemented Artificial Intelligence (AI) and Machine Learning (ML) tools at the point of care, few have successfully applied them to high-level decision making. A new frontier is expanding AI from artificial intelligence to augmented intelligence; traditional AI focuses on improving analytics efficiency while augmented intelligence is about improving the decision-making ability of healthcare leaders.
This article addresses the capabilities health systems should embrace and provides two examples of how AI can assist with leaders with their most important decisions. Healthcare leaders’ biggest needs of from AI are the ability to separate signal from noise and make decisions that impact the future.
To succeed in population health management (PHM), organizations must overcome barriers including information silos and limited resources. Due to the systemwide nature of these challenges, widespread stakeholder engagement is an imperative in population-based improvement.
An effective PHM stakeholder engagement strategy incorporates the following:
Includes as many stakeholders as possible at the beginning of the journey.
Meets the unique analytics and reporting needs of the organization.
Enables users to measure, and therefore manage, PHM outcomes.
Provides the real-time analytics value-based care requires.
With clinicians driving many of the decisions that affect health system quality and cost, they’re an essential part of successful improvement efforts. Clinicians are, however, notoriously overburdened in today’s healthcare setting, and getting their buy-in for additional projects is often a big challenge. To successfully partner with these professionals in improvement work, health systems must develop engagement strategies that prioritize clinician needs and concerns and leverage data that’s meaningful to clinicians.
Improvement leaders can approach clinician engagement on three levels:
Clinician-led local programs.
Department- or division-level programs.
Leadership-level growth and improvement programs.
The key to successfully leveraging artificial intelligence (AI) in healthcare rests not wholly in the technical aspects of predictive and prescriptive machines but also in change management within healthcare organizations. Better adoption and results with AI rely on a commitment to the challenge of change, the right tools, and a human-centered perspective.
To succeed in change management and get optimal value from predictive and prescriptive models, clinical and operational leaders must use three perspectives:
Functional: Does the model make sense?
Contextual: Does the model fit into the workflow?
Operational: What benefits and risks are traded?
To succeed in today’s rapidly evolving business environment, healthcare organizations must have accurate financial data. Approximately 50 percent of CMS payments are now tied to a value component; hospital operating margins are at an all-time low; and consumer demands are rising with their costs. In order to meet these new challenges, health systems must shift their strategy or risk being left behind. This article details the operational, organizational, and financial strategies that drive financial transformation, as well as examples of how to obtain and utilize financial data, find waste reduction opportunities, and much more.
Waste is a $3 trillion problem in the U.S. Fortunately, quality improvement theory (per W. Edwards Deming) intrinsically links high-quality care with financial performance and waste reduction. According to Deming, better outcomes eliminate waste, thereby reducing costs.
To improve quality and process and ultimately financial performance, an industry must first determine where it falls short of its theoretic potential. Healthcare fails in five critical areas:
Massive variation in clinical practices.
High rates of inappropriate care.
Unacceptable rates of preventable care-associated patient injury and death.
A striking inability to “do what we know works.”
Huge amounts of waste.
While over 90 percent of organizations in industries worldwide now use cloud computing in their operations, healthcare still lags behind. As health systems grow their ability to capture data, they still have only a fraction of the data they need to achieve today’s population health and precision medicine goals. Organizations looking to migrate to more agile cloud-based platforms and leverage data for measurable improvements can learn the fundamentals of this critical transformation in an e-book about the Health Catalyst Data Operating System (DOS™).
Patient comments such as “I feel dizzy” or “my stomach hurts” can tell clinicians a lot about an individual’s health, as can additional background, including zip code, employment status, access to transportation, and more. This critical information, however, is captured as free text, or unstructured data, making it impossible for traditional analytics to leverage.
Machine learning tools (e.g., NLP and text mining) help health systems better understand the patient and their circumstances by unlocking valuable insights residing unstructured data:
NLP analyzes large amounts of natural language data for human users.
Text mining derives value through the analysis of mass amounts of text (e.g., word frequency, length of words, etc.).
Healthcare is looking towards an era of personalized medicine in which providers customize treatments for the individual patient. Realizing this tailored level of care s a new level of data volume and analytics and AI capabilities that, while novel to healthcare, other industries are thriving in. Choosing the right role models as healthcare works towards the analytics- and AI-driven territory of personalized medicine will guide informed strategies and establish best practices.
With experience and expertise in these key areas, the military, aerospace, and automotive industries can serve as healthcare’s best examples:
The human cognitive processes of complex decision making.
The digitization of their industries, with the “health” of their assets as key drivers.
Operating in a “big data” ecosystem.
What can healthcare learn from Formula One racing? According to Dr. Sadiqa Mahmood, SVP of medical affairs and life sciences for Health Catalyst, race support teams leverage about 30TB of baseline data to create a digital twin of the car, track, and racer for simulation models that drive decisions at each race. Applied in the healthcare setting, a digital twin can help clinicians better understand each patient and their health conditions and circumstances in real time and make comprehensive, informed care decisions. But for the healthcare digital twin to happen, the industry must move away from data silos and towards a digital learning healthcare ecosystem.
The 2019 Healthcare Analytics Summit™ (HAS) was packed full of insightful discussions about data democratization, delivering healthcare in a digital age, and the future of analytics and AI. The 2019 HAS infographic reveals 1,600 industry leaders attended, with 60 percent of attendees from the IT/analyst industry, discussing trending data topics, interacting with presenters through polling mechanisms, and utilizing networking opportunities to share solutions and problem-solving methods.