Login Register Subscribe
Current Issue

Help

BI’s Article search uses Boolean search capabilities. If you are not familiar with these principles, here are some quick tips.

To search specifically for more than one word, put the search term in quotation marks. For example, “workers compensation”. This will limit your search to that combination of words.

To search for a combination of terms, use quotations and the & symbol. For example, “hurricane” & “loss”.

Predictive analytics emerges as workers comp best practice

Reprints

High-performing workers compensation claims organizations use predictive modeling eight times more frequently than firms with less success in closing claims, according to recent research on a practice that experts say has grown swiftly over the past decade.

“I think we are at a tipping point, at least in terms of using predictive analytics to improve claims management and claims practices,” said David Huth, Boston-based chief operating officer for Chicago-based Rising Medical Solutions, which provides medical cost containment and medical care management services to the workers comp industry. “I think it’s the future of the industry for a variety of reasons … we are in a data-rich industry, but we haven’t leveraged that data historically to make better and smarter decisions.”

Experts say data such as injured-worker demographics, injury data, timelines of claims and information on claims that end up in litigation can all help claims managers guide future outcomes.

Rising, which released a white paper Aug. 1, surveyed 1,700 claims professionals and narrowed down best practices among what it referred to as top-tier claims organizations: the top 24% of claims organizations that close claims at the same pace as opening them.

The survey found that such practices as measuring success and outcomes, investing in claims professionals and using an advocacy-based model for claims management lead to better outcomes and faster claims resolution. Advanced technology is also at the top of the list: warehousing data on injured workers, using outcome-based data to improve treatment, and measuring success — which all lead to predictive modeling.

Predictive modeling is not unlike the processes that can tell hurricane forecasters, using mounds of data and the paths of previous similar storms, where a certain hurricane is likely to hit — an analogy Jeffrey White, Rolling Meadows, Illinois-based senior vice president and product manager for workers compensation at Gallagher Bassett Services Inc., likes to use when he talks about the trend in managing care and outcomes for injured workers.

“The spaghetti models (for hurricanes) come out when the storm shows up, (and) it’s not always right but you kind of know you can start making preparations” depending on where you live, he said. “That it’s coming down the path, I know I have to get ahead of it … (With workers comp) what you are trying to do is take historical data and learn trends so that you can better understand what the possible outcomes will be.”

His colleague Sandip Chatterjee, Rolling Meadows-based senior vice president of product development for digital and advanced analytics at Gallagher Bassett, said the data is vast — and gets better over time, with the addition of new information such as age, type of injury, how the worker was injured, what events took place, what the medical visits entailed, what the doctor saw and said, and more.

“We are using the different data elements from the time the claim is reported to the time it deadlocks” before reaching a resolution, Mr. Chatterjee said, adding that outcomes and strategies are also noted and put into the algorithm of what works and what doesn’t. “Based on the outcomes, we have different forms of intervention.”

For example, an injured worker suffering from psychosocial issues related to the injury could help future similar claims. “We collect that information and try to run models on what would be the most likely outcome on the information we have,” said Mr. Chatterjee.

In addition, the data collected can help with claims workflow and prioritizing, said Mr. White.

“If you have tens of thousands of claims you are managing, predictive modeling is a powerful tool in prioritizing your claims,” he said.

Mark Moitoso, Atlanta-based executive vice president and risk practices leader at Lockton Cos. L.L.C., said predictive modeling is in place at nearly every organization he works with, but he cautions that experienced claims adjusters and managers are at the heart why it works.

“We highly encourage the use of predictive analytics in the claims mechanisms; it’s a way to improve the overall environment,” he said. “It’s a tool, but it’s not the tool.”

“We see the greatest value in the predictive modeling to guide us and target us into the claims that have the greatest potential for increasing costs,” said Paul Primavera, Washington-based executive vice president and national risk control services group leader at Lockton. “It is extremely helpful in pinpointing some issues that need to be looked at, but it does not take away the need for a (claims professional) to figure out what the next steps are to avoid the identifying factor (in increasing costs).”