Drill down in data for differentiation
One of the most important things workers' comp participants interested in getting the full benefit of predictive modeling can do is case mix adjustment, said Dr. Laura B. Gardner, president and founder of California-based Axiomedics Research Inc.
"It takes data analysis one step beyond looking descriptively and allows you to establish a relationship between predictive variables and outcome variables that adjust for differences among the claims."
Gardner says if you are trying to compare medical providers, it allows you to adjust for those providers that have more difficult caseloads. "If you didn't take that into account, you'd be doing providers a disservice because you'd be saying 'we expect your outcomes to be the same as those over here," she said. "That wouldn't be fair. So what this does is level the playing field and allows you to compare apples to apples."
Read more at the WorkersComp Forum homepage.
April 25, 2011
Copyright 2011© LRP Publications