Workers’ comp predictive modeling: A success story

After rolling out predictive modeling for medical claims management this year, Ahold USA Inc.—a supermarket chain with approximately 800 stores and 110,000 employees—expects to see annual savings in the low seven digits from workers’ compensation medical costs.

The expected savings is based on results from a pilot program in which the model was applied to 1,800 open claims last year. “What the model does so beautifully for us is that it identifies our problem claims in advance,” observed James Snell, the Director of Risk Management at Mac Risk Management Inc., the division of Ahold USA that manages workers’ compensation and general liability claims.

By addressing cost predictors on a per-claim basis, the model was able to project unpaid medical losses in 30-day increments, which resulted in immediate interventions to reduce claims severity. “The return on investment of a well-run predictive modeling program can be exponential,” he said. The effectiveness of predictive modeling depends on vast amounts of appropriate data. Ahold USA is in the enviable position of having a “treasure-trove of data” in its claims administration systems, said Snell, based on data collected since the company started self-insuring and self-administering in the 1980s.

The Ahold USA model uses claim characteristics, medical transaction details, and other data sources to reveal factors predictive of potential claims severity, said Rong Yi, a Milliman risk management and predictive modeling consultant.

Such indicators include multiple visits to doctors and the use of certain prescription drugs. The model then prioritizes claims that need special handling and medical case management, she noted. This helps injured employees receive appropriate medical care to reach maximum medical improvement and return to work sooner.

In traditional medical management, potentially problematic claims were generally difficult to identify and often judgmentally chosen using a manual process, Yi said. Predictive modeling is far more effective at detecting the claims that need immediate attention, she added. The company decided to focus on medical costs first because they were going up 8 percent a year. Wage replacement costs have been going up 5 percent annually, said Snell.

But this is just the beginning. Ahold USA plans to use this loss-mitigation approach to build predictive models to improve safety and risk management. The company is hoping eventually to learn enough to be able to offer more timely and appropriate return-to-work opportunities to its injured employees.

While implementing medical predictive modeling this year, the company intends to assess other, nonmedical aspects that could explain why injured workers are inclined to stay on workers’ compensation longer, Yi said. These factors include cost shifting from other disability benefit programs, attorney involvement, and the distance an employee lives from work.

Other tools, such as pain scales and questionnaires, also may be incorporated with the overall goal of maximizing employee safety, health, and wellness.

This success story is an excerpt from the article Workers’ Comp Predictive Modeling Comes of Age (And Not a Minute Too Soon), which appeared in the May/June 2012 issue of Contingencies, a bimonthly magazine published by the American Academy of Actuaries.

Learn more about Milliman’s workers' compensation claims predictive modeling services.