Tag Archives: triage

Claims Litigation: a Better Outcome?

Insurance companies have historically struggled with the challenges posed by claims litigation and the threat of attorney involvement in multiple lines of business. According to the Insurance Information Institute, 39 cents of every dollar spent in loss costs in commercial multi-peril went toward defense costs or containment. For medical professional liability, the number increases to 43 cents, and for product liability it is as high as 77 cents. For workers’ compensation (WC), where the employee gives up the right to sue the employer for injuries that happen in the workplace, that number amounts to 13 cents.

In 2014, the California Workers’ Compensation Institute performed an analysis of attorney involvement in California WC claims. Over the six-year period studied, attorneys were involved in 12% of all claims (including medical-only cases), 38% of lost-time claims and 80% of permanent disability claims. Although the report discussed multiple efforts by lawmakers to reform California’s WC laws to help reduce costs, the report noted: “Despite those efforts, the litigation rate has nearly doubled for all workers’ compensation claims, and more than tripled for claims involving lost time.”

With such large dollars at risk, it’s no wonder that companies are investing in claims system technology and the use of advanced analytics to help reduce the impact of litigation spend on their bottom line. This article will share how advanced analytics and data mining can be used early in the life cycle of a claim to help identify litigation-prone claims and triage them appropriately.

Setting the Stage

Cases with heavy litigation expenditures typically involve various parties connected in a complex way with differing and sometimes opposing incentives. The ultimate costs of litigation are driven by numerous, factors including the duration of the settlement discussions and trial, if applicable, cost of medical experts, discovery, depositions, attorney fees, responsiveness of the plaintiff attorney, impact of high/low agreements, the appeals process and more.

Therefore, insurance litigation comes with a number of challenges that have historically made it difficult to predict litigation outcomes (e.g. dismiss, defend, settle, alternative dispute resolution, probability of winning, etc.). Traditional approaches have tended to focus on historical reporting and backward-looking data analyses to understand litigation rates, costs, trends, etc. However, such “hindsight”-focused measures are reactive in nature. In many situations, it has been difficult to segment litigation outcomes, especially in the early days of a claim’s lifecycle when an adjuster can make a real difference in the trajectory of a claim. For that reason, a number of innovative insurers have begun shifting to more predictive and forward-looking solutions, including predictive analytics.

See also: Power of ‘Claims Advocacy’  

The Inspiration for Litigation Analytics

Insurance companies have largely been using data analytics to attack claim severity in lines such as WC, medical professional liability, general liability and auto liability bodily injury. By matching claim complexity with the appropriate resource skillset as early as first notice of loss (FNOL), a great deal of efficiencies have been introduced to help reduce claim durations and costs. Claim predictive models have helped insurers better segment and triage high severity workers’ compensation and bodily injury claims, driving up to 10-point reduction in claims spend.

Models focuse on claim severity can naturally be extended to other business areas including medical management, special investigative unit (SIU) referrals and litigation management. We have seen such claim cost models be used by extension in these other areas as more severe claims also tend to be the most complex. For example, the most expensive 10% of bodily injury claims as predicted by these severity models can turn out to be as much as six times more likely to go to litigation and be more expensive to litigate. In WC, the most expensive 10% of claims can turn out to be as much as three times more likely to go to litigation and be even more expensive to litigate. Clearly, there is plenty of segmentation power to be gained – even more so if the models are specifically developed to predict litigation.

Data Used

Data is the first building block of any analytics journey. The ability of actuaries and data scientists to effectively identify litigation-prone claims can be attributed to the power of advanced analytics, the growth of big data and inexpensive computing power and storage. The data used in developing litigation models is similar to that of claim-severity models. They include internal and external third party data, structured and unstructured data, direct pull fields and synthetically created variables. The large number and diversity of the data sources used, sometimes numbering in excess of a thousand potential candidate variables, provide unique information for segmentation and analysis, thus helping to answer the question: which combination of complex patterns seem to make a claim more prone to litigation?

Some of the data factors typically used in litigation models are quite intuitive and include claimant age and gender, accident jurisdiction, claim history, etc. Unstructured data such as the description of the injury and accident narrative are often valuable sources of information that may help to uncover indicators and behavioral clues that bear a strong correlation to future litigation likelihood. Text mining can be used to delve into such unstructured free form data and help identify co-morbidities that significantly drive up claim severity. Additionally, third party data commenting on the individual’s lifestyle and habits add a layer of information about the claimant that further helps to segment the litigation propensity of the claim.

Analytics Techniques Used

A number of modeling techniques can be used to predict the likelihood for a claim to move to litigation. There are a number of techniques that generally perform well if used in a robust end-to-end modeling process that actively involves the end users from day 1. From multivariate predictive modeling and machine learning techniques to neural networks, various methodologies are available to identify the most predictive variables. However, and as we noted in the article titled “The Challenges of Implementing Advanced Analytics,” it is important to balance building a high precision statistical model with being able to interpret and consume its results. Our experience has shown that it is more valuable to leverage less complex models that are easily interpretable to the end-users than going after highly precise and complex models that are hard to consume and understand.

Models are typically trained on historical data with a defined target variable (i.e. what the model is trying to predict). Example target variables could be a binary 0-1 field (indicating if a claim has indeed moved to litigation “1” or not “0”), litigation dollars explaining how expensive are the claims that are already in litigation, a proxy for each, or a combination of both. Models are also validated on a holdout sample of claims to assess the robustness of the model.

Not surprisingly, models could be built and developed leveraging data available at FNOL or day 1, helping insurers take expedited business actions and make important decisions early in the lifecycle of the claim. As additional data becomes available through time, these models benefit from added information to make their prediction in the weeks and months that follow.

See also: 2 Steps to Transform Claims, Legal Group  

Claims Systems Are Differentiators

With the newest claims systems being implemented, insurance companies are achieving better claim outcomes and spending less on loss adjustment expense. The days of claims systems being only record keeping solutions are passé. The newest technology helps claimants directly verify the status of their claim regardless of the time of day or person’s location, through self-service portals and intuitive websites. But, these capabilities are not just for “external” system users alone. “Internal” system users can now leverage advanced analytics and spend less time on administrative tasks (e.g., manually populating spreadsheets), shifting their focus to working with insureds and improving their claims experience.

Litigation Models in Action

A number of models can be built to identify which claims could be more complex and involve litigation. As an example, an insurance company could build a model that answers the following questions: Of the claims that go to litigation, which ones are likely to be most expensive? If the model returns a high score, it means that the claim has a high likelihood of costing the insurance company a lot of money in litigation expenses. Therefore, it would suggest that the most experienced internal resources and attorneys should be focused on this claim.

Data used and target variables

For the case study at hand, a population of more than 10,000 bodily injury claims spanning multiple accident years was studied. For each claimant, many characteristics and factors about the claim, claimant, accident, injury, suit details (if the claim is litigated) were collected and recorded in a database. External third party data such as the vehicle identification number (VIN) and geo-demographic and behavioral data at the household and census block level were also added to capture more information.

The target variable (i.e. what the model is trying to predict) was calculated as all dollars spent on litigation, including attorney fees and expenses. A predictive model was then built employing a standard train, test, validation methodology.

Model results and output

The resulting models exhibited strong segmentation across the holdout sample. For example, the litigation costs for the highest-scoring 10% of claims were almost double the average population, while the lowest-scoring 10% of claims had litigation costs that were less than half the cost of the average claim. This strong segmentation is even more impressive considering it was realized at day 1, not weeks or months into the life of the claim.

The model contained about 30 predictive variables, some of which were intuitive and readily available (e.g., claimant age and gender, accident location and type – whether parking lot or intersection, etc.). The model also included information sourced from third party vendors (e.g., census employment statistics) and proxies for behavioral factors (e.g., the distance between the accident location and claimant’s residence, lag of time before reporting a claim, etc.). External geo-demographic data about the claimant were also beneficial (e.g., population density in the zip code of residence), in addition to data available from the National Highway Traffic Safety Administration (NHTSA) regarding fatal accidents statistics about the accident Zip code, etc.

Bringing Models to Life

Building a predictive model like the one described above is important but only beneficial if the model helps change behaviors, decisions and actions. The insights derived from these models help insurance companies take direct actions on their claim triage strategies, attorney selection and defense strategies. Business rules can be carefully crafted to help claim examiners in their decision-making process. When an adjuster understands that a high-scoring claim has a higher risk of moving to litigation and costing more, defense strategies can be adjusted accordingly. From assignment of external defense counsel, to settle or defend decisions based on case dynamics, insurance companies can alter their event management, resource allocation and escalation decisions earlier in the lifecycle of the claim.

See also: Rethinking the Claims Value Chain  

Carpe Diem With Analytics

The claim insurance landscape is becoming more complex, competitive, fast-moving and disrupted. There is little doubt that the adoption of big data, data science and analytics is important to becoming more agile in this environment, helping insurance companies make better decisions within days of receiving a claim. With the underwriting cycle indicating another period of softening rates, and interest rates hovering at record low levels, tapping savings in litigation spend might just be what the doctor ordered for insurance companies brave enough to seize the opportunity. As Larry Winget said in his book It’s Called Work for a Reason, “Knowledge is not power; the implementation of knowledge is power.” The knowledge and analytics exist today to improve litigation costs. We believe the time has come to implement that knowledge.

As used in this document, “Deloitte” means Deloitte Consulting LLP, a subsidiary of Deloitte LLP. Please see www.deloitte.com/us/about for a detailed description of the legal structure of Deloitte LLP and its subsidiaries. Certain services may not be available to attest clients under the rules and regulations of public accounting.

This communication contains general information only, and none of Deloitte Touche Tohmatsu Limited, its member firms, or their related entities (collectively, the “Deloitte Network”) is, by means of this communication, rendering professional advice or services. Before making any decision or taking any action that may affect your finances or your business, you should consult a qualified professional adviser. No entity in the Deloitte Network shall be responsible for any loss whatsoever sustained by any person who relies on this communication.

How Telemedicine, AI Are Transforming Care

Dr. David Dantes, a retired ER doctor in his 70s, still manages to work six hours a day starting at 6:30 am and sees about 20 patients per day. His lifetime of medical experience would be ending if he hadn’t joined a telemedicine platform earlier this year. Meanwhile, after a long day of flu-season patients, Dr. Linda Anegawa also uses a telemedicine system to talk to three more patients who couldn’t meet in person. As a doctor on a virtual platform, she’s been able to build amazing trust with many patients who keep coming back for her.

Both Dr. Dantes and Dr. Anegawa are Stanford-trained physicians who believe in providing quality care and convenience to patients. Primary care is often not accessible for seniors and busy patients, and a visit to the ER can be traumatic and expensive. Telemedicine can solve these pain points by bringing care to patients wherever they are and whenever they need it, while smoothing out the logistics of scheduling and traveling, so doctors can focus on their top priority of delivering care. Similarly, health AI holds the promise of increasing efficiency in the care process for improved care outcomes and better time management.

Telemedicine – Bringing Top Quality Care to Patients Conveniently and Efficiently

Telemedicine is not new. There are a large number of companies including Teledoc and other well-funded private companies such as American Well, MDLive and Doctor on Demand that offer telemedicine solutions. Many of the hurdles facing these companies are related to lack of focus on physician quality and low utilization due to patient education, and rolling out services through employer insurance programs doesn’t help. Multiple research and studies have shown that only two out of every five consumers have heard of telemedicine. Utilization rate is even lower at less than 5% across the industry and less than 2% in many companies.

If telemedicine truly delivers on the promise of bringing quality care and convenience to patients, why are adoption rates so low? This past summer, I conducted a survey with 561 participants across the U.S. and found that although 95% of respondents have never used telemedicine, 57% are interested in trying if key concerns could be addressed. Topping the concerns is the quality of physicians, which suggests that telemedicine providers with high-quality physician networks are much better positioned to have high adoption and utilization rates.

PlushCare (GGV portfolio company), the telemedicine platform where both Dr. Dantes and Dr. Anegawa operate, has addressed this issue by building a physician network that only includes doctors from the top 50 medical schools in the U.S. This patient-centric approach with an emphasis on physician quality is seeing a dramatic uptick in both adoption and repeat visits.

See also: Telemedicine: Fulfilling the Promise  

Now that we’ve outlined the needs and primary adoption barrier of consumers, let’s look at what motivates doctors to use telemedicine, because ultimately doctors are the key to the quality of the service. Beyond the scheduling flexibility, companies like PlushCare also offer a suite of tools to help doctors operate more efficiently — from handling the back-end administrative work to streamlining the front-end patient visits — so doctors can focus on what they do best and enjoy doing the most, delivering care to patients. That’s why we see physicians like Dr. Dantes bringing his years of experience back to practice through telemedicine, and others like Dr. Anegawa taking online patient visits beyond her practice.

A common misperception about telemedicine is that the primary target audience is either those who live in rural/underserved areas, or millennials who seem to do everything online. In reality, telemedicine has much broader applications for consumers beyond these groups. Most telemedicine users fall in the age of 35 to 45, with busy work and travel schedules and families with multiple kids. Telemedicine can provide a hassle-free way of seeing a doctor with a lot of flexibility in time and location.

The use cases can even be extended to schools, which are often understaffed with onsite medical professionals, or nursing homes when the seniors have acute symptoms. Instead of sending the patients to ER or waiting for a family member, telemedicine can address many of the problems within 10 to 20 minutes and involve family in the discussion in a three-way call. Most importantly, the convenience doesn’t need to come at the cost of quality.

AI – Doctor’s Silver Bullet to Boost Productivity and Improve Outcome

While telemedicine drives the much needed efficiency to healthcare by simplifying logistics around the care process, health AI targets the care process directly to increase productivity. At the current stage, health AI may not be able to displace doctors and originate treatment plans independently, but it’s more than ready to help doctors allocate time more efficiently depending on individual patient needs, and keep tabs on patients post-visit to improve outcomes and lower readmission rates.

For example, start-up company Lemonaid Health provides a “traffic light” system using an AI model developed by physicians to do the first round of screening on patient cases. Cases are categorized into three pipelines upon screening: “Green,” or straightforward, cases account for 80%; “yellow,” or complex, cases account for 15%; and “red,” or extreme, cases account for the remaining 5%. This categorization allows doctors to spend less time on straightforward cases and focus on patients with more complex situations.

Another example is Carbon Health, which leverages AI to examine and triage patient cases pre-visit through a chatbot interface. Based on the complexity of the cases, Carbon’s AI assistant books an appropriate amount of time for the visit and shares the pre-visit synopsis with the doctor so he or she can dive right into the problem during the visit. The AI assistant also follows up with patients post-visit to keep track of key indicators and resurface cases to the doctor when anomalies are detected.

See also: It’s Time to Embrace Telemedicine  

I am excited to see consumer-centric digital health companies that are providing broader access and better quality of care, and bringing efficiency to the process. Consumers are increasingly engaged in issues about their health and are expecting healthcare tech improvements. Meanwhile, tech innovators are continuously disrupting the status quo. I believe consumers are at the forefront of these changes, and innovators behind consumer-centric digital health companies can win big in this market.

If you are a healthcare founder making solutions to transform consumer experience, I’d love to talk to you.

Rethinking the Claims Value Chain

As a claims advisor, I specialize in helping to optimize property casualty claims management operations, so I spend a lot of time thinking about claims business processes, activities, dependencies and the value chains that are commonly used to structure and refine them. Lately, I have been focusing on the claims management supply chain — the vendors who provide products and perform services that are critical inputs into the claims management and fulfillment process.

In a traditional manufacturing model, the supply chain and the value chain are typically separate and — the supply chain provides raw materials, and the value chain connects activities that transform the raw materials into something valuable to customers. In a claims service delivery model, the value chain and the supply chain are increasingly overlapping, to the point where it is becoming hard to argue that any component of the claims value chain couldn’t be handled directly by the supply chain network.

image5
Which creates an intriguing possibility for an insurance company — an alternative to bricks and mortar and company cars and salaries, a virtual claims operation! Of course, there are third-party administrators (TPAs) that are large and well-developed enough to offer complete, end-to-end claims management and fulfillment services to an insurance company through an outsourced arrangement. That would be the one-stop shopping solution: hiring a TPA to replace your claims operation. But try to envision an end-to-end process in which you invite vendors/partners/service providers to compete to handle each component in your claims value chain (including processing handoffs to each other.) You select the best, negotiate attractive rates, lock in service guarantees and manage the whole process simply by monitoring a performance dashboard that displays real time data on effectiveness, efficiency, data quality, regulatory compliance and customer satisfaction.

You would need a system to integrate the inputs from the different suppliers to feed the dashboard, and you would also need to make certain the suppliers all worked together well enough to provide the ultimate customer with a seamless, pain free experience, but you are probably already doing some of that if you use vendors. You would still want to do quality and compliance and leakage audits, of course, but you could always hire a different vendor to do that for you or keep a small team to do it yourself.

Your unallocated loss adjustment expenses (ULAE) would become variable, tied directly to claim volume, and your main operating challenge would be to manage your supply/value chain to produce the most desirable cost and experience outcomes. Improved cycle time, efficiency, effectiveness, data accuracy and the quality of the customer experience would be your value propositions. You could even monitor the dashboard from your beach house or boat — no more staff meetings, performance reviews, training sessions — and intervene only when needed in response to pre-defined operational exceptions.

Sounds like a no-brainer. Insurance companies have been outsourcing portions of their value chain to vendors for years, so why haven’t they made their claims operations virtual?

If you are running an insurance company claims operation, you probably know why. Many (probably most) claims executives are proud of and comfortable with their claims operations just the way they are. They believe they are performing their value chain processes more effectively than anyone else could, or that their processes are “core” (so critical or so closely related to their value proposition they cannot be performed by anyone else) and thus sacrosanct, or that they have already achieved an optimal balance between in-house and outsourced services so they don’t need to push it any further. Others don’t like the loss of control associated with outsourcing, or they don’t want to consider disruptive change. Still others think it might be worth exploring, but they don’t believe they can make a successful business case for the investment in systems and change costs. Unfortunately, this may help explain why claims executives are often accused of being stubbornly change averse and overly comfortable with the status quo, but I think it is a bit more complicated than that — it all begins with the figurative “goggles” we use to self-evaluate claims operations.

If you are running a claims operation, you have an entire collection of evaluation goggles — the more claims experience you have, the larger your collection. When you have your “experience” goggles on, you compare your operation to others you have read about, or seen in prior jobs, or at competitors, to make sure your activities and results benchmark well and that you are staying up to date with best practices. At least once a year, someone outside of claims probably demands that you put your “budget” goggles on o look for opportunities to reduce ULAE costs. or legal costs, or fines and penalties, or whatever. You probably look through your “customer satisfaction” goggles quite a bit, particularly when complaints are up, or you are getting bad press because of your CAT response, or a satisfaction survey has come out and you don’t look good. Your “stakeholder” goggles help you assess how successful you have been at identifying those who have a vested interest in how well you perform, determining what it is they need from you to succeed, and delivering it. You use your “legal and regulatory compliance” goggles to identify problems before they turn into fines, bad publicity or litigation, much as you use your “no surprises” goggles to continually scan for operational breakdowns that might cause reputational or financial pain, finger pointing and second guessing. Then there are the goggles for “management” — litigation, disability, medical, vendor — and for “fraud mitigation” and “recovery” and “employee engagement.” Let’s not forget the “efficiency” goggles, which help you assess unit costs and productivity, and the “effectiveness” and “quality control” goggles, which permit you to see whether your processes are producing intended and expected results. And of course your “loss cost management” goggles give you a good read on how well you are managing all three components of your loss cost triangle, i.e., whether you are deploying and incurring the most effective combination of allocated and unallocated expenses to produce the most appropriate level of loss payments.

Are all those goggles necessary? You bet. Claims management involves complex processes and inputs and a convoluted web of variables and dependencies and contingencies. Most claims executives would probably agree it makes sense to regularly evaluate a claims operation from many different angles to get a good read on what’s working well , what isn’t and where there is opportunity for improvement. The multiple perspectives provided by your goggles help you triangulate causes, understand dependencies and impacts and intelligently balance operations to produce the best outcomes. So even if you do have a strong bias that your organization design is world-class, your people are the best and all processes and outcomes are optimal, the evaluation should give you plenty of evidence-based information with which to test that bias and identify enhancement opportunities — as long as you keep an open mind.

No matter what you do, however, there will always be others in your organization who enjoy evaluating your claims operation, and they usually aren’t encumbered by such an extensive collection of goggles. They may have only one set that is tuned to budget, or customer experience, or compliance, or they may be under the influence of consultants whose expensive goggles are tuned to detect opportunities for large-scale disruptive/destructive process innovation or transformation in your operation. On the basis of that narrow view, they just might conclude that things need to change, that new operating models need to be explored. Whether you agree or disagree, your evidence-based information should be of some value in framing and joining the debate.

Will we ever see virtual claims operations? Sure. There are many specialized claims service providers operating in the marketplace right now that can perform claims value chain processes faster, cheaper and better than many insurance companies can perform them. The technology exists to integrate multiple provider data inputs and create a performance dashboard. And there are a few large insurance company claims organizations pursuing this angle vigorously right now. I fully expect the companies that rethink and retool their claims value chains to take full advantage of integration of supply chain capabilities and begin to generate improved performance metrics and claim outcomes, ultimately creating competitive advantage for themselves. Does that mean it is time for you to rethink your claims value chain? I think the best way to find out is to put on your “innovation” goggles and take a look!

When to Use a Nurse-Triage Program?

How many claims justify using a nurse-triage program? This is a good question that seems simple but actually can be answered in many ways.

How Much You Spend on Claims Matters More Than How Many There Are

Here is a rule of thumb based on our experience over many years: most insureds who have 100 or more claims per year find triage to be justifiable by any measure, regardless of their industry or state. The savings from avoiding unnecessary claims and from improving in-network utilization far outweigh the cost of the triage call.

Many organizations with fewer than 100 claims also find triage to be financially justifiable. Here’s an example. If an insured has 24 claims a year averaging $2,000 each, it would spend $48,000. Even a mediocre triage service could help avoid 25% of claims, saving $12,000. (A top triage service could save almost twice as much!) The 24 triage calls would cost less than $2,400, yielding a net savings after triage fees of $9,600. In actuality, many claims cost much more than $2,000 each, meaning the triage service would save even more than $9,600, and additional savings in claims administration fees and productivity are also often realized.

The determining factor in cost justification is usually what an insured spends on claims, rather than its number of claims. High claims costs justify triage faster.

Other Considerations:

– Those that are self-insured realize the savings from triage immediately. Even on referrals that become claims, good triage providers improve in-network utilization, generating savings on medical fees. Top-tier triage providers also direct referrals to the right level of care (e.g. an occupational health clinic vs. an emergency room), generating additional savings.

– Employers in fully insured programs may think that they cannot benefit from triage because they incur the cost but the savings accrue to their carrier. In fact, employers save in several ways, though it takes time. Here is one example: Employers improve their experience modifier, which significantly lowers their premium cost in the future.

– Some insureds in time-sensitive industries with specialty jobs calculate that triage’s ability to help keep workers on the job is worth more than the claims savings.

– One of the most important considerations is the medical outcome – call it the “human factor.” The best triage service is focused on getting the right care for the injured employee. Sometimes, that means early identification of a serious condition or an unrecognized risk, and making a referral that creates a claim because it’s the right thing to do for the injured employee.

Bottom line: Insureds can justify triage in a variety of ways, not just by cost or claims count. The quality and consistency of the triage provider is a key factor, too – poor triage risks poor clinical outcomes, disgruntled employees and extra costs.