Predictive Modeling Helps Drive Improved Claim Outcomes

Reducing Claims Cost While Providing Best-In-Class Support

By Laurie Barkhorn
For risk managers of large companies, managing the cost of workers' compensation is a top priority. Industry best practices help injured workers recover from their injuries and facilitate their return to work while reducing the overall cost of claims. But forward-thinking insurance companies and risk managers don't stop there. They continually seek new ways to improve outcomes. The Hartford is an industry leader in this regard and continuously experiments with innovative ways to manage claims cost down while providing best-in-class support to injured employees.

This article is part of a series in which we share some of The Hartford's initiatives that are designed to drive better outcomes for our customers.

Predictive modeling is transforming how claim examiners identify and manage high-risk workers' compensation claims, and yielding results that are helping to reduce return-to-work timeframes and claim costs. Vice President and Claim Data Scientist Paul Drennan is a driving force behind The Hartford's innovative approach to predictive modeling, which informs the company's comprehensive solutions for workers' compensation claim intervention and management. I sat down with Paul recently to discuss predictive modeling and why it is such a critical value proposition for large, loss-sensitive companies.

LB: Tell us about your role within The Hartford and how it fits into The Hartford's larger claims management strategy.

PD: I lead the practice of data science and predictive modeling at The Hartford. Essentially, I oversee an "analytical factory" supported by a team of data scientists and engineers which is responsible for analyzing large amounts of data and extracting both predictive and prescriptive knowledge from that data. The team plans, builds and deploys predictive models for The Hartford's claims departments, and also monitors their effectiveness and directs their evolution. Our goal is to match claim profiles to our sophisticated predictive models and create a path leading to the best possible claim outcome.
LB: What is predictive modeling and why is it important for workers' compensation claims?
PD: Predictive modeling is a technology that uses data analytics to identify potentially high-risk claims before they become volatile. Volatile claims are those that tend to spiral into a costly succession of complex conditions that the examiner could not have anticipated upon first review, whether due to the nature of the injury, treatments, third parties such as a medical provider or attorney, or other risk factors that present barriers to recovery.
On average, only three to four percent of workers' compensation claims are deemed volatile, but they can generate 50 percent of a company's loss costs, according to The Hartford's statistics. Predictive modeling helps handlers identify these claims and take corrective action before they escalate.
LB: How do predictive models work?
PD: Predictive models perform advanced statistical analysis based on historical and current claim data. They run continuously, monitoring the various characteristics of a claim and zeroing in on signs of volatility as soon as they arise, and excel at finding nuanced combinations of loss characteristics, including common patterns and those that are truly unique.
The system flags claims with potential complications and atypical conditions, allowing the claim handler to evaluate cases proactively and intervene with timely resources and services to aid the claimant's recovery and hasten the claim's resolution.
LB: How is predictive modeling different from traditional claims management?
PD: Workers' compensation claims are traditionally managed using rule-based best practices that have been codified over years of claims experience. These practices are highly effective for the majority of claims. However, many claim decisions are based on the handler's own judgment and experience. Less obvious exposures – such as unnecessary treatment, psychological issues and unanticipated developments – can escape notice.
Predictive modeling augments traditional claims management by providing objective data that handlers need to make fact-based decisions. This relatively new approach to claim management is only possible because of recent advancements in technology.
LB: What kind of technological advances make predictive modeling possible?
PD: Workers' compensation claims are data intensive, and expansions in data capture capabilities have advanced to the point where we now have the ability to collect, store and manage the large volume of data that strong predictive models need. 
With sufficient data and powerful computational tools in hand, data scientists and engineers who specialize in predictive analysis can create models for a range of insurance needs, including help in identifying potentially volatile claims, fraud, subrogation and other conditions. Each model is designed to bring together unique combinations of data – such as loss and treatment plans, environmental factors and time periods – to discover patterns, identify outliers and recommend next best steps for the claim handler to better manage claims.
LB: What is The Hartford doing that is different than other carriers?
PD: At The Hartford, we're continuously seeking opportunities to refine our existing models to make them smarter, and we re-teach our models as claim conditions change. These system capabilities are augmented by patented text mining algorithms that are able to identify potential risk factors that have been captured within the claim handler's notes.
The model will “nominate" a claim for review, prompting the claim examiner to review its risk factors, evaluate new developments and intervene when necessary. This in turn generates activities that support faster claim resolution and return to function for injured workers. The Hartford has integrated predictive modeling into its operational work processes and implemented strategies to help the claim examiner address barriers to recovery in an effective way.
LB: How would the claim examiner intervene on a nominated claim?
PD: The claim examiner can tailor intervention to the nuances of an individual case. For instance, the examiner may assign the claim to the most experienced adjusting, medical and legal resources; increase the level of management review; engage a nurse case manager; or bring in a medical professional who can help make treatment changes. Or the examiner may deem it necessary to conduct a drug review, obtain a second opinion or provide return-to-work coordination.
Optimally, the claim team fosters a relationship with each claimant that allows for a customized solution – not just for the claimant's injury but also to address other barriers to recovery such as addiction, chronic pain, anxiety or depression. Predictive models can assist here, too, drawing out claim-related conditions that might ordinarily remain hidden.
LB: Can you provide an example?
PD: Imagine an employee slips and falls on wet flooring at work and injures his back. His doctor prescribes physical therapy and painkillers, and advises that the employee should be safely back to work within a few weeks.
Unbeknownst to the claims examiner and the doctor, the employee is facing personal issues that are taking a toll on his emotional well-being and lacks the motivation to take charge of his recovery. He takes the medication prescribed for pain relief but misses most of his physical therapy appointments. When weeks pass without any improvement to his back condition, the doctor orders an MRI. Surgery is recommended. To make matters worse, the employee has become dependent on the pain medication.
In this case, lack of incoming claims for physical therapy could prompt the model to issue an alert. Upon investigating the matter and its cause, a behavioral therapist could be assigned to help the employee work through the personal issues that may be preventing him from taking charge of his health.
LB: How is this improving claim outcomes?
PD: Predictive modeling helps put the right claim into the right process and assign the right resources at the right time. This enables claim teams to deliver the attention that volatile or complex claims require and minimize over-handling claims that are more routine.
The effects may not be obvious to the employer, but when predictive modeling achieves its goal, employers realize earlier closure rates for claims and faster return-to-work timeframes for their employees. Their cost of risk is also likely to go down. This is especially true for risk managers and insurance buyers with large deductibles given that they share a significant part of the workers' compensation risk.
Predictive modeling helps to ensure that claimants receive the timely, targeted support they need beginning with day their claim is filed through its resolution.
LB: Any best practices to share?
PD: When evaluating a potential insurance carrier, risk managers should first look for insurers whose models are based on years of historical claim information. Robust models are built on data. More data is better. Models that capture the fine details of claims in process will be better equipped to reveal hidden factors and identify potential outliers.
Successful intervention is equally essential. The insurer should have the expertise needed to respond with an action plan that delivers results.
Finally, it's one thing to have data science available, but more important to find an insurer with a demonstrated track record of implementing predictive modeling algorithms effectively in their workflows. The real magic happens not when the analyst designs the program, but when the business uses it to its fullest advantage to drive better decisions and outcomes.

About Paul Drennan

Paul Drennan is vice president and predictive analytics lead in the data science unit at The Hartford. With more than 20 years of experience establishing and leading data science teams across multiple industries, Drennan focuses on marrying world class analytics with deep process knowledge in large scale operations to create sustained profitable changes in business practices.
The information provided in these materials is intended to be general and advisory in nature. It shall not be considered legal advice. The Hartford does not warrant that the implementation of any view or recommendation contained herein will: (i) result in the elimination of any unsafe conditions at your business locations or with respect to your business operations; or (ii) will be an appropriate legal or business practice. The Hartford assumes no responsibility for the control or correction of hazards or legal compliance with respect to your business practices, and the views and recommendations contained herein shall not constitute our undertaking, on your behalf or for the benefit of others, to determine or warrant that your business premises, locations or operations are safe or healthful, or are in compliance with any law, rule or regulation. Readers seeking to resolve specific safety, legal or business issues or concerns related to the information provided in these materials should consult their safety consultant, attorney or business advisors.
The Hartford® is The Hartford Financial Services Group, Inc. and its subsidiaries, including Hartford Fire Insurance Company. Its headquarters is in Hartford, CT.
1 National Accounts In Force as of August 2016