At the annual HIMSS conference in Orlando this year I spent some time talking to Paul Bradley, Chief Data Scientist for ZirMed. Paul shares his insights on the growing importance of using predictive analytics in revenue cycle management. You can also listen to the podcast of my interview.
HIMSS17 Highlight – Paul Bradley
Predictive analytics is a topic that seems to get bigger and bigger each year at HIMSS. How should healthcare organizations be leveraging predictive analytics to realize more revenue in 2017?
Excellent question. So, in the last decade or so, healthcare providers have really invested in their data systems through meaningful use and other incentives. Hospitals now collect a wide breadth of data all around the patient, the patient encounter, what doctors are working on the patient, what procedures are being done to them, what drugs they’re taking, a number of other data elements. And that is the raw material for us to apply this technology called predictive modeling, where we look at historic data and try to find patterns and trends around certain events of interest. So, for example, will a patient pay for a portion of their bill they’re responsible for? Is it likely that a certain charge is missing on a claim, indicating that care was given to a patient, but for a number of reasons the codes to actually bill for that procedure, drug, or device don’t end up on the claim?
So what we’re doing is taking this data that healthcare providers are collecting as part of their day-to-day operations, applying this predictive modeling technology to it to find those places where either revenue is being left on the table, or a provider might be underpaid, and finding those situations and allowing them to go and recoup that revenue.
You talk about collecting data. Does this occur in real time and why is that important?
Paul: A lot of the systems are collecting data in real time. EHRs are collecting data at near real time or in real time. Clearly, you know, laboratory systems are. And a lot of that data then goes through a process where it’s coded and normalized to produce a claim. And a lot of the work we’re doing on the financial end, in the revenue cycle area of healthcare, is looking at that financial data and seeing where the gaps might be and leveraging that information and say, “How do you fill those gaps and fill that revenue in where you might have been missing it before?”
So what’s next? What’s coming down the pike for you guys?
So in the same aspect of finding revenue that is left on the table, we do a lot of work with large hospital systems, and one of the trends that we’re seeing is large hospitals systems are acquiring doctor practices, which brings together two somewhat diverse datasets. And we’ve been able to merge those datasets together to get a more wide view of the patient and the experience that goes on. So to look for consistencies between doctor charging and the charging that the institution does, and we call that solution Professional Charge Integrity, merging data from the professional care that’s given and also from the institutional care that’s given to see that the care across both of those spectrums and make sure that false positives, that might come from one dataset, we’re able to weed those out by leveraging the other dataset from the professional side.
And this is a new solution from you guys, right?
Yes, this is a brand new solution coming out this year and we’re announcing it here at HIMSS. People can learn more on our website, www.ZirMed.com.