This story originally ran in McKnight’s Long-Term Care News on May 28, 2019
By Billie Nutter, president of Casamba
“Analytics” has certainly become a buzzword in the healthcare industry in recent years. But analytics should not be viewed as an all-encompassing term for any type statistical or data research. There are different types of analytics depending on the needs of the user and the resources – data, technology and others – available to them.
What cannot be argued is the value that analytics, regardless of type, can provide to healthcare. As healthcare changes toward outcome and value-based payment initiatives, analyzing available data will help reveal which practices are most effective, cut costs and improve the health of the populations served. While acceptance of analytics in healthcare remains low, with just 3 percent of long-term and post-acute care audiences using technology-based analytics tools (Black Book, 2017), demand for this type of information is growing. Global healthcare analytics spending is projected to grow nearly 16% annually through 2022, according to a 2017 study from BCC Research (2017).
Employing data to help improve patient outcomes and manage operations more efficiently is, itself, nothing new. The healthcare industry has always been data reliant. Data can render insights on system resource issues, labor management and clinician performance, and identify patients at risk for re-hospitalization or exacerbation of conditions. Ultimately, post-acute caregivers will seamlessly and securely share data across all care settings, collaborate on the most effective treatments and reduce costs while improving outcomes.
So let’s take a look at where we are today and where we’re going in the world of analytics.
The present: Descriptive analytics
Data analytics, if applied properly, will help improve patient care in the post-acute health care system. Descriptive and diagnostic data is interesting and certainly worth looking at. It provides a historical look at your organization, operational efficiencies and patient outcomes. This can provide some value within the company, but it is far from enough to drive improvements in an organization down to the individual patient.
To drive change, you have to understand your own data ecosystem, not somebody else’s that is, at best, a rough facsimile of your organization. There are too many variables and variations in healthcare delivery right now that add too much noise to the data to make comparative analytics as valuable as some advocate.
The future: Predictive analytics
As healthcare organizations develop more sophisticated big data analytics capabilities, they are beginning to move from basic descriptive analytics towards the realm of predictive insights.
Predictive analytics helps users determine what might happen next. Instead of simply presenting information about past events, predictive analytics estimates the likelihood of a future outcome based on patterns in historical data. This allows clinicians and other healthcare providers to recognize potential events before they happen, and therefore make more informed choices about how to proceed.
Examples of such include, predicting potential hospital readmissions based on the probability of a person suffering the same ailment again. It can also predict when and why patients are readmitted when a patient needs behavioral health care.
But before we start believing that predictive analytics is going to change the healthcare world, we need to understand how it works, technically and programmatically. Without protocol and patient-specific outcomes data, predictive analytics cannot be useful in a broad manner.
The goal: Prescriptive analytics
New approaches to healthcare delivery, often resulting from regulatory change, are increasingly complex and driving competition. Pressure to do more with less is making the case for a way to quickly determine what actions should be taken to optimize outcomes and reduce costs. Prescriptive analytics offers healthcare decision makers this opportunity.
Based on decision optimization technology, these capabilities enable users to not only recommend the best course of action for patients or providers, but they also enable comparison of multiple “what if” scenarios to assess the impact of choosing one action over another.
A key characteristic of prescriptive analytics is the need for many large data sets. The healthcare industry is, therefore, an industry that sees a lot of potential in the latest addition of analytics. Healthcare providers will use prescriptive analytics to sift through multiple complex iterations of treatment protocols, provide solutions to reduce avoidable hospital readmissions, segment patient variables (e.g., demographics, socioeconomics), identify health trends, and assess other related data sources to optimize outcomes. Only a handful of organizations and industries have that amount of data and data sets to make something useful out of it with prescriptive analytics. However, in 5-10 years will be as normal as business intelligence today.
The road ahead
The healthcare industry is quickly adopting the use of analytic tools and formulas to gain competitive value and reduce the cost of poor decision-making. In a recent study by Deloitte, enterprise executives said that business analytics are already helping them make better decisions, optimize their operations and improve outcomes. Eight in 10 executives claim a positive ROI from their analytic efforts and 78 percent said analytics helped to improve workflows and increase productivity. Delivering value for patients must become the overarching goal, with value defined as the health outcomes achieved per dollar spent. Only when we truly measure outcome the same across care settings will we be able to yield meaningful data – the kind of data that makes a difference in population health.
For more information about Casamba Analytics, please visit our web page.