Dan Ward, Vice President Strategy, ZirMed in Louisville, Ky.: There are trends, patterns, and information available to you in your own data that can be leveraged to great end. Uncovering these insights, however, requires something far more technologically sophisticated than simple manual analysis.
For example, when a given medication is administered (or not administered) in conjunction with three other interventions, patients over a given age who have been in the hospital for X number of days have a 93 percent probability of readmission — unless a specific other intervention occurs.
The same challenges — and the same kinds of opportunities — exist on the financial side. For example, you can predict the likelihood of a claim being denied or rejected before that claim even goes out the door. A machine-learning algorithm can say: given these attributes, given these diagnoses codes and this payer, there is a 98.3 percent likelihood this claim will be denied. Moreover, changing certain data elements would reduce that probability by a factor of five.
These are incredibly powerful pieces of information, but they‘re very difficult to get at as a manager, a nurse, or a doctor in the old-fashioned manual process — even if you were to spend months combing through the data.
More articles on health IT:
5 health IT key notes: Biggest EHR vendor stories of 2015; DOD contract modifications; searchable HIPAA violation database launches; new data breaches
10 most-read health IT stories of December
ONC releases interactive map-style compendium of state health IT policy levers
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
