NU Online News Service, Aug. 18, 10:07 p.m. EST
Liberty Mutual says it has evaluated hundreds of thousands of lost-time claims and millions of medical billing transactions to enhance its predictive model for workers' compensation claims costs, which are growing faster than inflation.
The Boston-based insurer says it has analyzed its database to come up with highly predictive variables to identify potential high-cost workers' compensation claims—a challenge for brokers, agents, and buyers.
The insurer says it ran more than 200,000 lost-time claims through the model to prove its accuracy after assessing 825,000 lost-time claims and 140 million medical billing transactions.
What is being billed as Liberty Mutual’s “next generation predictive model” can identify these claims as early as claim intake, says George Neale, general manager of claims for Liberty Mutual’s Commercial Markets segment.
“In addition, we continuously assess the risk of escalation of our entire inventory through several modeling stages,” he explains in a statement. “Arming our claims handlers with this information gives us a unique opportunity to apply strategies and expert resources at a point in time where they maximize our ability to achieve the best possible outcome for injured workers and our policyholders.”
The new model is the latest edition to VantageComp, the insurer’s approach to claims management. Liberty Mutual created one of the first workers' compensation claim-cost models in 2004.
Beyond medical and billing data, Liberty Mutual’s Center for Disability Research says it can identify psychological and social issues, as well as co-morbid medical conditions. The model can look at all data points together and over time to analyze the impact on a workers' compensation claim.
According to the National Council on Compensation Insurance (NCCI), the average indemnity cost of a lost-time claim grew 47 percent over the last decade. The medical portion of this type of claim increased 95 percent during the same time period, from $14,200 in 2000 to $27,700 in 2010.
