Among its many data-oriented initiatives, CNA is applying big data technology to workers compensation claims and adjusters’ notes.
“That is a classic, unstructured big data kind of problem,” says Nate Root, SVP of CNA’s shared service organization. “We have hundreds of thousands of workers compensation claims, and claims adjuster notes, and there is tremendous value in those notes.”
Root says the insurer recently began identifying workers’ compensation claims that have the potential to turn into a total disability, or partial permanent disability, without the right sort of attention. By examining the unstructured data, CNA has developed a hundred different variables that can predict a propensity for a claim to become serious, and then assign a nurse case manager to help the insured get necessary treatments for a better patient outcome, get them back to work and lower the overall cost of coverage.
For example, the program can find people who are missing appointments or who are not engaged with physical therapy and should be. “We are not prescribing medical treatments,” Root says. “We get the nurse case managers involved to work cases they ordinarily would be working, but three or four months sooner.”
CNA is using a variety of technologies, including mainframe-based financial information, Root says, as well as Guidewire ClaimCenter. “We have enabled text mining off the claims adjusters’’ notes, we run that through our predictive modeling approach with SAS and R, the open source statistical analytical software,” he adds.
The algorithm runs at specified times in the claims’ life span, and if flagged, those claims enter a different triage routine. “We have 20 different categories of claims. On some we use red’, yellow’ and red.’ The red claims are obvious to anyone. The green are expected to remain non-serious. And the yellow ones could go either way. That’s where we want to spend the most attention,” Root explains.
Root says this is merely the latest big data application for CNA, which also has been using big data techniques on underwriting, pricing and market analysis, to identify where opportunities could be developing. CNA also is continuing to explore the vast amount of data available for purchase. “It is fairly staggering,” Root says, “as is discerning what’s predictive and what’s just noise.”
