Analytics

Data Diving to Improve Comp

More companies are harnessing industry data to cut down claim duration and overall cost.
By: | September 14, 2015 • 7 min read

Predictive analytics in the workers’ compensation space is having an evolutionary moment.

Dean Foods, a food and beverage company, first developed an analytical model for its return-to-work program back in 2010.

“The model was very simple at that time. It was basically an indicator of lost time or no lost time,” said Kevin Lutzke, director of risk management at Dean Foods.

Advertisement




The company’s TPA uploaded daily updates to a data warehouse, where return-to-work coordinators could see which claims were indicated as possible lost-time claims and required their attention.

That early model, built in-house by a company actuary, yielded an 80 percent accuracy rate, and “moved the needle” on the company’s transitional duty program, getting more injured workers back in the game faster.

“It got to a point where everybody was so good at identifying which claims were going to be lost time or not, and the RTW coordinators were able to facilitate transitional duty so well, that we actually changed our culture at Dean,” Lutzke said. “The attitude used to be, ‘They’re not coming back until they’re 100 percent.’ Now we always try to keep people working with transitional duty.”

Three years later, Dean Foods implemented an updated version with third party administrator Helmsman Management Services, which factors in a wider variety of details about each case, including the worker’s age, type of injury, classification as surgical or non-surgical, and comorbidities.

“The attitude used to be, ‘They’re not coming back until they’re 100 percent.’ Now we always try to keep people working with transitional duty.” — Kevin Lutzke, director of risk management, Dean Foods

It also asks for input on social factors, such as the worker’s family situation, personal finances, and the status of his or her relationship with the employer.

Those elements may indicate tendencies to depression and isolation, which would prolong recovery, or that the worker might purposely lengthen the time away from work.

“Those details are kept confidential, to protect the employee’s privacy,” Lutzke said. “We don’t see that information as the end user, but we receive an overall score from the TPA.”

The more detailed model also allows Dean Foods to expand its applications from a simple lost time indicator. The company now uses its output to measure reserve levels against what it typically spends on a claim of a particular severity — a figure based on Helmsman’s database and book of business.

“We’re only seven or eight months into this, so we don’t have enough information yet,” Lutzke said. “We’ll have to wait a few more months to see if we’re focusing on the right things.”

The evolution of the food company’s predictive model and its applications reflects an industrywide trend. Less than a decade ago, modeling programs for workers’ comp simply spit out a score on a scale of one to 10, ranking a claim’s likelihood of becoming long-term and expensive based on a few factors specific to the injury in question. Standard metrics have traditionally included type of injury, body part injured, age of the worker, gender and comorbidities.

But models include a much wider scope of demographic variables that can impact an injured worker’s path to full recovery, such as the worker’s ZIP code, the average income of that area and the level of access to health care institutions.

Some models also incorporate information about prescribers — what type of pain medication they dispense, their general prescribing patterns and who refers patients to that prescriber.

Companies can adapt a predictive model’s various functions to address more specific areas of interest and pinpoint trouble spots.

For some, a model might highlight chronic overspend on pharmacy costs, while for others it might indicate a need for a better way to triage claims up-front and get the right resources on the case more quickly. Models exist to determine which claims would benefit from nurse case management and which might be subject to subrogation.

Clinical Applications

Helios, for example, launched a pilot predictive analytics program in 2011 that identified claims likely to result in high pharmacy costs, which would then be targeted with specific interventions. Measured against a control group that received no interventions, the pilot group saw a 26 percent total cost reduction, as well as a shorter duration of pharmacy utilization.

Joe Anderson, director of analytics, Helios

Joe Anderson, director of analytics, Helios

“We know there are some prescribers who, if an injured worker with a higher level of severity goes to see them, there’s a correlation with higher long term pharmacy costs and longer claim duration,” said Joe Anderson, director of analytics at Helios.

In a situation where an injured worker has several prescriptions for opioids, Helios launches a fairly non-invasive intervention: sending a letter to the prescribers to alert them of possible drug abuse.

“It can go all the way to medication review, or peer-to-peer intervention,” Anderson said. “Sometimes the doctor will talk to the treating prescriber and figure out how to change the regimen.”

Advertisement




That model has also been enhanced several times.

“Over the past few years, we’ve had an expanded data set with more customers, which gives us opportunities to fill in gaps of information and measure things we weren’t previously able to measure,” Anderson said.

Other models help detect fraud, said Scott Henck, senior vice president and actuary, claim actuarial and advanced analytics, at Chubb Insurance.

Some claims are flagged for potential “soft fraud” if there are indicators that the worker is malingering and simply not progressing at the rate the model predicts he or she should.

Medical codes on the claim bill can also tip off an adjuster when a worker may be taking advantage of workers’ comp care to get treatment for a separate, unrelated injury or illness.

“Codes for significant but unrelated conditions might give us reason to investigate further,” Henck said.

Chubb’s original model hit the market in 2008, and has since undergone several updates. Currently, the insurer sees average cost savings in the 5 percent to 10 percent range, which stems from identifying fraud early as well as more effectively directing the right resources toward potentially risky claims.

“Sometimes it’s very obvious which claims are high or low severity. It’s more about identifying which claims are likely to develop in their severity and address it early to mitigate the exposure,” Henck said.

Developing targeted strategies early in the claim life cycle is a key benefit, said Stephen Allen, managing director of commercial insurance services at Crystal & Company.

“The strength of modeling is that you know early on that a claim has the potential to be dangerous, and can get a senior adjuster involved to make sure more resources are used for high risk, high severity claims,” Allen said.

“Any time you can get earlier involvement, there’s a much higher likelihood you get a worker back to work quickly,” he said.

Data Depth and Detail

Of course, a model is only as good as the data fed into it. The length and richness of claim history varies from provider to provider, but larger TPAs and insurers with developed tools typically have a large data set with 10 to 15 years’ worth of history.

“The customization and client-specificity are very important in determining what’s predictive and relevant,” said Chris Flatt, leader of Marsh’s workers’ compensation center of excellence.

Origami Risk’s analytics combine data sets from multiple sources: its own aggregate data, the client’s data including claims history, and third-party information such as evidence-based disability guidelines, said Aaron Shapiro, executive vice president of Origami Risk.

Henck said that data sources could even expand to include information gleaned from social media.

Expansion of data sources “should be able to increase the depth and precision of solutions as well as open up possibilities for new solutions,” he said.

Interventions

One challenge that remains in predictive analytical models is making the data output easily consumable and actionable by a broad-spectrum consumer base comprising claims adjusters, insurers, data scientists and risk managers.

“We present metrics on the individual claim that indicate how quickly a particular injured worker should be back to work,” Shapiro said. “We also produce trend lines based on an aggregate of claims so that an individual case can be compared to the average claim duration and cost for a particular injury.” That allows users to identify outliers and intervention opportunities.

“We present metrics on the individual claim that indicate how quickly a particular injured worker should be back to work.” — Aaron Shapiro, executive vice president of Origami Risk.

Interventions implemented based on a model’s output might involve deciding who would benefit from nurse case management, sending a letter or otherwise intervening in the treatment plan set forth by a prescriber, or adjusting reserve levels.

Advertisement




“Analytics is still a very complex subject and there’s still a lot of confusion in the marketplace, due to different terms being used in different ways,” Helios’ Anderson said.

The varied availability of data and many ways analytics can be used likely add to the confusion. Savings can also be hard to determine because that involves estimating costs that are never actually incurred.

But given the pace at which companies have developed analytical programs, the role of predictive analytics in workers’ comp seems bound to grow.

Katie Siegel is an associate editor at Risk & Insurance®. She can be reached at [email protected]

More from Risk & Insurance

More from Risk & Insurance

Catastrophe Risk

Material Resiliency

New materials, methods and ideas are empowering property owners to rein in their catastrophe risks.
By: | October 12, 2017 • 11 min read

The 2017 hurricane season is one for the record books. Rebuilding efforts are underway, with builders working to make insureds whole again as soon as possible … at least until the next storm comes along.

Advertisement




And therein lies the problem with recovery in disaster-prone regions. It evokes the oft-quoted definition of insanity: Doing the same thing over and over again and expecting a different result.

So what if we did it differently? What if instead of rebuilding to make structures “like new,” we rebuilt to make them better, more resilient, less prone to damage?

The reality is, we don’t really have a choice. Climate change is ushering in weather systems that are increasingly volatile. Wildfires are raging like never before. Sea-level rise is threatening our coasts, and there’s no way to dial any of it back.

Nevertheless, people will continue to build homes and businesses along the coast. Real estate developers will continue to nestle luxury homes into wooded foothills.

That means communities need to come to terms with the risk and plan for it intelligently.

Michael Brown, vice president and property manager, Golden Bear Insurance

“Natural disasters are going to happen,” said Michael Brown, vice president and property manager with Golden Bear Insurance. “But if we plan and build communities around the idea that something bad may happen someday, then that community can bounce back faster afterward.”

In any natural disaster, he added, “the property damage is extreme. But the biggest portion of the losses, both insured and uninsured, are the time element pieces. How long was the business closed? How long were homeowners unable to occupy their homes? Those are the pieces that drag on for months — years in some    cases — and really drive the economic loss.”

That’s the motivation behind new materials, designs and strategies being implemented in the construction and repair of at-risk residential and commercial properties.

Powerful Flood Solutions

Newer building products move the needle significantly in terms of efficacy.

For new or restored structures in flood-prone regions, Georgia Pacific produces gypsum panels that incorporate fiberglass mats instead of paper facings and comply with the latest FEMA requirements for flood damage resistance and mold resistance. Wall boards made from magnesium oxide (MgO) don’t absorb water at all and have the added benefits of being environmentally friendly and non-flammable.

In the UK, advanced flood-resilient structures built with water-resilient concrete-block partitions are being fitted with not only MgO wallboards, but also wood-look porcelain or ceramic flooring that’s non-permeable and fire-resistant — without sacrificing aesthetics. Drains are installed in the flooring, along with sub-flooring gullies and submersible pumps that push the water back outside. Outlets and appliance motors are all situated above expected flood levels. Doors are equipped with sliding flood panels.

In the event of flooding that exceeds a depth of two feet, automatic opening window panels (flood inlets) are triggered by sensors to allow flood water to enter the property slowly, to reduce external pressure that could damage the structure.

Carl Solly, vice president and chief engineer, FM Global

Controlled inflow buys time for a homeowner to raise furniture up on blocks, or for a business owner to raise pallets of goods up to higher shelves or move equipment to a higher elevation.

Water intrusion is reduced dramatically, and even when it happens, there is little to no damage. Water is pushed into the floor drains, surfaces are allowed to dry, and then it’s back to business as usual in days rather than months — likely with no insurance claim filed.

Dramatic improvements are happening on this side of the pond as well. For entities that need permanent on-site flood solutions, barriers like flood gates and retractable flood walls are the most sophisticated they’ve ever been.

After suffering $4 billion in damage during Superstorm Sandy, New York’s Metropolitan Transit Authority invested heavily in flexible fabric flood panels that are made with Kevlar® and can be unrolled quickly and easily. Additional flood gates hinged to air grates are passively activated by the weight of incoming water entering the grates.

Advertisement




The transit authority is also testing a prototype “resilient tunnel plug” — essentially a giant air bag that can be deployed quickly to seal off sections of subway tunnel. The plug is designed to withstand not only flood but also biochemical attack.

Even temporary solutions are leaps and bounds beyond the days when sandbagging was typically the best option. New as-needed barrier methods include inflatable bladders that can be placed around a building’s perimeter and filled with water to keep floodwater and flood debris at bay.

“People have always said, ‘Well, I’m in a flood plain, it’s inevitable. It’s an act of God,’ ” said Carl Solly, vice president and chief engineer, FM Global. “In the last several years, we’ve really been trying to deliver the message that you can do something about your flood risk.”

Shake, Pummel and Burn

Flood is far from the only problem benefiting from smart engineering. FM Global is working with manufacturers to develop and certify roofing material designed to better withstand the localized hailstorms that often plague southeastern and midwestern states.

Current materials rated for severe hail can withstand hailstones up to 1 ¾ inches in diameter. The new product, rated for “very severe” hail can tolerate hailstones up to 2 ½ inches. The difference sounds small, but it’s far from it.

“It’s about three times the amount of impact energy when it hits the roof [compared to a 1 ¾ hailstone],” explained Solly. “That’s a big difference.”

As for “bouncing back” after a catastrophic fire, Solly said that’s a fairly tall order. But even there, technology is helping to reduce the severity of fires so that disruption is minimal.

FM Global researchers recently pioneered the concept of SMART sprinklers — shorthand for Simultaneous Monitoring and Assessment Response Technology — which can sense a fire earlier than traditional systems and activate targeted sprinkler heads when needed and shut off once the fire is out.

“You’ll catch it with less water, so from a water usage perspective, a water damage perspective and a smoke damage perspective, we think that has an opportunity to be a big difference-maker in the fire protection industry, particular with high-challenge fires,” said Solly.

“You’ve got a better chance of stopping what normally would be a really tough fire to catch.”

In addition, added Brown, smarter sprinkler systems, much like burglar alarms, could be programmed to notify the fire department instantly, even when a structure is unoccupied.

For earthquake risk, said Brown, resilient building efforts are less about new materials than they are about more strategic ways of using traditional materials.

“Here in California we wrap homes in stucco around the wood frame to help the whole building move as a unit. Stucco is concrete so it does crack. I end up with a building that’s got some cosmetic damage … but you don’t have to rebuild the building. It does its job in terms of absorbing a lot of the ground motion before it pushes the building beyond its design tolerances.”

Using stronger, larger steel brackets where the walls meet the roof or the floor or each other, said Brown, “keeps the north wall from moving in one direction while the west wall moves a different direction.”

Those kinds of stress points can push modest earthquake damage to catastrophic levels, he said.

One earthquake innovation still in the beta phase is a project out of the U.C. Berkeley Seismological lab, using the accelerometers in smartphones as virtual seismometers. Participating phones have an app that detects certain types of ground motion. As phones pick up earthquake wave patterns, they ping the server which checks nearby smartphones to see if they sensed the same pattern, all in microseconds. If an earthquake pattern can be confirmed, an alarm will be sent to every cellphone within a logical radius.

That might only buy people an extra two to five minutes before the event, said Brown, “but if you are the operators of Bay Area Rapid Transit commuter trains, that’s enough time to slow all the trains down to five miles an hour. If you are Google, that’s enough time to park a bunch of hard drives in your server farm so that they’re better able to resist shaking and not be damaged too badly.”

Raising Standards

Cost, of course, will impact the take-up of resilient materials and tools. If it’s three times more expensive to build a home out of the resilient materials, a lot of builders aren’t going to want to because the home will be tougher to sell.

Advertisement




FM Global’s Approvals division tests and certifies a variety of products aimed at mitigating disaster peril. That can help increase property owner confidence in these materials, particularly for commercial structures.

“When you’re betting millions of dollars and the future of your business — or at least the near-term future of your business — you really need to know that it’s going to work,” said Solly.

With just-in-time manufacturing, a company may have a few days’ worth of stock on hand rather than three months’ worth.

“So you can’t afford to be out of business for weeks, because your customers are going to go somewhere else for your product,” he said.

Building standards and codes can help drive adoption of resilient measures in both commercial and residential construction. But more work needs to be done to raise standards to meet the goal of resilience.

Effecting real resilience is something leaders across the spectrum should be talking about, including brokers and carriers, government and research agencies, building products manufacturers, and corporate executives.

If lives are saved in an earthquake, but a building is still damaged to the point where it needs to be torn down, said Brown “that building owner, that community, is going to have a much longer path to full recovery. We want the building codes strengthened to an immediate occupancy [goal] — we want people to be able to move right back into that building so there’s a much shorter window of disruption.

“It’s certainly better for me as the insurer,” he said, “but it’s even better for the guy that owns the building or runs his business out of it because now his employees still have a place to come to work and they can still get paid.”

Every single business able to minimize its downtime in this way helps the entire community be more resilient, he added. It creates that snowball effect in a good way. When businesses are able to stay open or reopen quickly, he said, workers don’t lose a meaningful amount of pay. Everybody’s in a better position to continue shopping and supporting the local economy.

“If you just shorten the line of people who are looking for some sort of federal aid, or state aid because they’ve had a massive financial disaster — maybe we can turn those into moderate to small financial disasters. That’s the key, I think, to communities being more resilient.”

Driving Demand

As the likelihood increases that property owners will experience a second loss or even third loss, some insurers are looking at ways to invest in resilience — a smarter long-term business plan than paying to rebuild again and again.

One new initiative is Lex Flood Ready, the product of a partnership between Lexington Insurance and The Flood Insurance Agency (TFIA). Flood Ready is a coverage enhancement for Lexington Private Market Flood clients that will not only indemnify property owners that suffer flood damage but will also provide the funds to rebuild them to a higher standard of resiliency when replacing floors and walls.

Advertisement




Resilience proponents advocate a variety of approaches to encourage take-up, including tax credits, resilience grants, insurance incentives and other partnerships, as well as encouraging lenders to engage borrowers by making the flood risk assessments part of the mortgage process.

A certification scheme similar to LEED could also help drive resilience efforts. The UK is currently beta-testing a certification program called Home Quality Mark, developed by the Building Research Establishment (BRE). Properties are rated on stringent criteria that considers not just disaster resilience, but energy performance and cost, durability and environmental impact.

“Getting people from diverse perspectives thinking about it and talking about it is going to be the avenue to finding the right answers.” — Michael Brown, VP and property manager, Golden Bear Insurance

That’s something builders would be able to use to add value to their properties, offsetting the cost of building in resilience and driving consumer demand for properties built to the highest standards.

With increased resilience will come questions for insurers, said Brown. “It will open up a can of worms.”

It will create something of an arms race among insurance companies, he said. “Who’s going to be the first one to figure out what’s the right way to insure that? What’s the right price? What are the right terms and conditions?” Admittedly, it’s a good problem to have.

Effecting real resilience is something leaders across the spectrum should be talking about, including brokers and carriers, government and research agencies, building products manufacturers, and corporate executives.

“Getting people from diverse perspectives thinking about it and talking about it is going to be the avenue to finding the right answers,” said Brown.

“That kind of mentality top to bottom in the industry is going to be necessary. It’s not the first time we’ve dealt with disruptive things and we will continue doing it. It’s what keeps the game interesting.” &

Michelle Kerr is associate editor of Risk & Insurance. She can be reached at [email protected]