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”.

Login Register Subscribe

Deep data pools create opportunities for improved outcomes, cost savings

comp costs

Data-rich workers compensation records are a fertile field for analytics that can direct claims to adjusters and others best-suited to manage them, help identify qualified doctors and attorneys, and provide other insights.

The results for insurers and employers are healthier workers and lower costs, among other benefits, sources say.

Predictive analytics aid the decision-making of adjusters, said Virna Rhodes, Marlton, New Jersey-based senior vice president, workers compensation claims, for Liberty Mutual Insurance Co. and its Boston-based third-party administrator Helmsman Management Services LLC.

“Data analytics are only as good as the people who use them,” she said. Used effectively, they can help “get the claim in the hands of the right expert at the earliest opportunity.”

Ms. Rhodes said Liberty Mutual’s claims systems “are just awash in notes and data” that artificial intelligence analyzes to flag claims based on potential severity, the likelihood of an injured employee returning to work, compensability of a claim, and whether subrogation is likely or fraud could be present.

Analytics can generate significant savings, sources say.

“You’re trying to get the claim to the right person at the right time,” said Adam Wesson, director of claims solutions at Verisk Analytics Inc.’s North Reading, Massachusetts-based ISO Claims Partners. “The sooner you involve the right resources in handling the claim, the better the outcome you’re likely to have.”

Skip Brechtel, executive vice president and chief information officer at Cannon Cochran Management Services Inc. in Metairie, Louisiana, said an analysis by Cannon several years ago showed that claims with two or more comorbidity factors cost as much as seven times more than those without them. In 2014, CCMSI began using an algorithm that considered 70 comorbidity data fields to help determine whether indemnity claims could become severe and require closer management attention.

“And that’s how we got started on this path” that led CCMSI three years ago to begin pushing around 400 claims data elements and other information daily to Boston-based analytics provider Gradient AI Corp., where artificial intelligence identifies drivers of claims costs, predicts outcomes and provides guidance for reserve-setting.

 “As we all know, artificial intelligence in the use of predictive analytics has come on greatly in the last four to five years,” Mr. Brechtel said.

Stan Smith, CEO of Gradient AI, said its insurer and TPA clients typically shave from 3% to 5% off claim costs, with some seeing savings of as much as 14%. “It’s been very strong in all cases, but it’s been very substantial in certain cases,” he said. 

“These models get smarter the more data that you give them,” said Joe Powell, senior vice president of data and analytics at Gallagher Bassett Services Inc. in Fort Wayne, Indiana. The TPA feeds its machine-learning model with medical billing, diagnoses and other claims-related information to create tens of millions of records that can be used to study outcomes.

A valuable use of analytics is to help identify doctors and lawyers who are contributing to favorable outcomes for employers, Mr. Powell said.

Gallagher Bassett selects its network medical providers based on outcome and quality data, he said. 

Providers are evaluated and rated on how closely they adhere to medical-based guidelines when treating injured workers, Mr. Powell said. “And then we’re able to rank and rate our providers on how often they’re treating by the book,” he said.

“It’s very similar on the law firm side,” Mr. Powell said. “We look at the cases they are handling and the outcomes that they drive and we measure their performance.”

For both doctors and attorneys, “we’re adjusting those outcomes based on the complexity of the cases they are handling,” Mr. Powell said. An algorithm ensures physicians and lawyers handling mostly complex cases are not necessarily ranked lower than those with simpler and easier to resolve cases, he said.

Analytics can also help manage the risk of workplace injuries, Mr. Wesson said. The models provide “a whole wealth of information” that employers can use to identify the type, frequency and severity of injuries among their workers, he said. By uncovering those trends, risk managers can better understand how to prevent injuries.

The structure of the models varies.

“The most primitive approach might be to set up a handful of business rules and call them predictive models,” an approach that could have some value, said Joel Raedeke, Chicago-based chief technology and data science officer at Crawford & Co.’s TPA Broadspire Services Inc. “That’s sort of a window-dressing approach that I’ve seen.”

A more robust approach is to build a multivariate predictive model, which is powerful and, if properly maintained, can integrate new features as they are developed over time, Mr. Raedeke said.

Such models can be expensive and labor intensive unless they take advantage of artificial intelligence to keep them current, he said.






Read Next

  • High-stakes cyber claims demand quick action

    The biggest difference between handling cyber claims and more traditional property/casualty claims is the speed with which the process unfolds, which demands an immediate, coordinated response by the policyholder, insurer and broker, observers say.