Originally published in Becker’s Hospital Review
By Tony Colarossi
The amount of data produced in hospitals has grown exponentially in recent years, to such an extent that many health systems suffer from an information overload that is making everything from surgery to radiology departments less efficient.
The problem for health systems is that, with so much information being created, aligning which pieces of data are the most important to a defined strategy becomes paramount to success. Organizations that manage to find the data that really matter and learn how to use the information to facilitate actionable change can fix some of their most pressing problems.
That may sound expensive, but it’s an outcome that can often be achieved using the health system’s existing often under-leveraged software applications.
It’s about separating out the noise. As journalist Nate Silver wrote in his book, The Signal and the Noise, “The signal is the truth. The noise is what distracts us from the truth.”
Many health systems already have the software tools they need to perform this type of work, such as Tableau or Qlikview, in house. However, few know how to use these tools effectively. Why? Because giving someone oil paints, brushes and an easel doesn’t transform them into Leonardo da Vinci. Finding the right data in a health system, running analytics and presenting it in a visual way is a specialty where consultants can help.
The key to starting this process is to identify bite-sized pieces of data that can make a real difference and then use data visualization tools to put that information in front of the people that initiate directives and change.
Done the right way, data visualization presents the information that matters to the people that can use it, to improve behavior and outcomes.
Identifying the biggest pain points in a hospital, appropriately measuring the problem and the solution and qualifying the correlated issues and dependencies that are creating the problem can produce results that add up to significant margin improvement.
For example, at one large metro area health system, data highlighted specific problems that would make a significant difference if resolved. Critical problems included surgeries taking longer than the average time of the last 10 procedures, flagging surgeries that started more than 20 minutes late, and tracking the slow turnover of an operating room. Data revealed that 23 percent of the time it took more than 40 minutes to turn over an operating room. Getting that number down to 20 minutes (the optimal time) would allow for an additional 1,100 hours of surgery time annually. Achievement toward these types of improvements can add up to significant additional revenue.
At another hospital, data highlighted where revenues were being lost as a result of the organization failing to bill for every item. For example, a radiology procedure that requires isotopes had no charge for isotopes in 1 percent of cases, resulting in lost charges of $25,000. Another radiology billing code typically associated with surgical charges failed to bill those fees 0.25 percent of the time, causing a $46,000 revenue loss. Individually, these problems might seem small, but they’re easily mitigated using data and analytics, and using data to find the 50 largest areas of this type of unbilled activity identified opportunities worth more than $1 million.
Beyond repairing problems, new analytic approaches can foresee the future, too. Data analytics and Artificial Intelligence can crunch past data to be predictive, suggesting when staffing problems typically occur or flagging patients that are frequent users of emergency room services when other more cost-effective treatments would be more appropriate.
As health systems learn to use big data to boost their operational and administrative efficiency, that same approach can be applied to medicine, helping enable the industry’s shift from a fee-for-service model to payments based on improving patient outcomes.
As Accenture’s Jeff Elton wrote in Harvard Business Review, “While the most visible immediate benefit (of data and analytics) is cost reduction, the real motivation is a patient-centric business model — one that recognizes that health and care management needs to occur wherever the patient is, not just in hospitals or physician offices.”
As daunting as leveraging big data may sound, it all starts with separating the signal from the noise and making one small improvement at a time.
Tony Colarossi leads Plante Moran’s acute healthcare consulting services.