Sponsored Content: Optum Workers’ Compensation and Auto No-Fault

Answers to Your Most Common Questions About Predictive Analytics in Workers’ Comp

Predictive models improve clinical outcomes and reduce costs for payers, but only if you know how to use them.

Predictive analytics models have a number of cost-saving applications in the world of workers’ compensation prescription management.

These models are used operationally in helping to identify patients for home-delivery fulfillment programs which are less expensive than retail, saving money on the cost of prescriptions. Algorithms assist in routing claims to the most appropriate case handler based on claim complexity or personnel experience, which increases operational efficiency.

Perhaps more importantly, “predictive analytics help to identify problems before they arise,” said Tron Emptage, R.Ph, MA, Chief Clinical Officer, Optum Workers’ Compensation and Auto No-Fault.

For example, a predictive model can raise red flags after detecting unusual prescribing patterns of a physician or inconsistencies in a claimant’s typical refill pattern. Alerting claims professionals to this data allows communication with both patient and provider, proactively mitigating future consequences like extended claim duration and over-utilization, which could lead to adverse drug interactions or addiction.

But for insights delivered by analytical tools to be effective, they must be paired with clinical expertise. Predictive analytics platforms can show potential paths forward on a claim and their likely outcomes, but they can’t make decisions alone. And, according to the experts at Optum, nor should they.

“Using analytics in combination with clinicians is how we effect change,” said Joe Anderson, Director of Analytics and Data Science. “Clinical expertise is an integral, not supplementary, component of leveraging data-driven insights to produce better outcomes both medically and financially.”

This may leave workers’ compensation claim payers wondering how best to integrate predictive analytics in their operations to generate the best outcomes from both clinical and cost perspectives. Here, Emptage and Anderson answer the seven most common questions companies ask about predictive analytics:

1. What is “predictive analytics” and how does that differ from other analytical tools?

Joe Anderson, MBA, Director or Analytics and Data Science, Optum Workers’ Compensation and Auto No-Fault

There are no technical or scientific definitions for terms like predictive analytics, artificial intelligence, or machine learning, and the distinctions between them are fluid as technology continues to evolve.

“The simplest way to define predictive analytics is using an algorithm to make a decision. Data scientists will see fine distinctions between different platforms and tools, but the differences ultimately come down not to the technology, but how you use it,” Anderson said.

The key feature of predictive analytics is that it is forward-looking, meaning it evaluates several alternative decisions and projects their potential outcomes to aid in real-time decision making.

Traditional data analytics platforms, on the other hand, examine past data to identify trends and patterns.  They are used for observation and learning, while predictive platforms are used to drive action.

2. What are the benefits of a forward-looking platform versus one that examines the past?

A traditional data analytics platform will help users spot correlations between different trends and make determinations about their common drivers. A particular medication, for example, may correlate with longer claim duration or higher costs, and one specific physician may be the source of those prescriptions.

The insights generated by traditional data analytics, however, are unchangeable. They provide a retrospective look at what’s already happened, but don’t always point to a way forward. Predictive analytics algorithms suggest immediate actions that can proactively alter the course of a claim.

“Predictive algorithms project the costs that an injured worker will generate in the future, and show what elements are driving that trend. In this case, there’s a more immediate judgment call to be made,” Anderson said.

“For example, if $50 was spent on a prescription last month, that number is what it is,” Emptage added. “A predictive model shows us how to spend less in the future. It’s not prescriptive on what decisions to make, but will help highlight the options and potential outcomes of those options.”

3. What data is most important for predictive analytics?

Tron Emptage, R.Ph, MA, Chief Clinical Officer, Optum Workers’ Compensation and Auto No-Fault

Identifying potential problems before they arise requires pulling together disparate data to create a holistic picture of a patient.

“Pharmacy data is most important,” Emptage said. “This includes the prescription data itself and the prescriber writing it, and whether the patient is seeing any other providers also writing prescriptions, similar or different.”

The injured worker’s diagnosis factors largely in the overall severity of a claim and in a predictive model.  Even with a simple injury, supplemental data like previous medical history and comorbidities may indicate increased risk of a complicated and extended recovery. Psychosocial variables, including a patient’s social support network and general outlook on their recovery, also are strong indicators of how the claim will progress.

“Personal demographics may have some predictive value, but that information isn’t always as useful as what they’re getting in terms of medical treatment,” Emptage said.

4. With so much data available, why is clinical expertise necessary?

Predictive models were first built based on dollars. They could predict claim cost, but treatment decisions are based on much more than just the price tag. Clinical experts look beyond dollar signs to help make decisions that will produce the best medical outcomes for patients while balancing payers’ need to contain costs.

“You may have all the data in the world, but we are dealing with human beings, and clinical experts make sure we keep the human element of care,” Anderson said.

Clinicians can also spot when a model’s output simply doesn’t make sense.

A predictive model could, for instance, raise a red flag over a spike in a claimant’s morphine equivalency dose. “It may have missed, though, that the patient just had surgery,” Anderson said. “A clinical expert will see that and make sure there’s not an overreaction.”

“Predictive analytics is both an art and a science,” Emptage said. “We have the data, the algorithms, the output from models, but those results may turn out false positive or false negatives. Clinical expertise helps to weed out the false results.”

5. What are false positive and false negatives?

As in the above example, a model may produce a false positive if it indicates a problem where there is none, either due to incomplete data or simply due to a wrong prediction. Dedicating time and resources to solve a problem that never existed or never materializes can ultimately drive up the cost of a claim.

False negative may have more serious consequences. This is when a problem goes unnoticed and unaddressed. For example, a claimant may be taking excessive dosages of addictive painkillers due to concurrent prescriptions from different prescribers — but the model won’t pick up on this risk if it doesn’t have a complete list of the claimant’s providers.

“False negatives end up being even more costly because it usually means more care and a longer recovery,” Emptage said. “We don’t want to miss something that turns into a creeping catastrophic claim.”

This again is where a clinician’s input could make a pivotal difference. A trained expert will be able to spot the warning signs of addictive behavior even when the data says otherwise.

6. What are some predictive analytics best practices?

Using predictive analytics effectively comes down to three things: data, talent, and leadership.

Maintaining a database of historical data is necessary to feed a predictive model and ensure accurate results. “You can’t build models to predict the future if you don’t have data on what’s happened in the past,” Anderson said.

A model’s success is likewise dependent on the ability of specialists to interpret its findings and improve the algorithm over time. The model’s output should be continually compared to historical trends to identify deviations, and the algorithm should be adjusted accordingly.

Finally, a strategic commitment at the leadership level is critical.

“There will always be new types of data and treatments, products, clinical guidelines and regulations evolve. You have to be nimble and responsive to changing environment, and willing to keep an open mind about acting on data-driven insights,” Emptage said.

7. How will predictive analytics evolve in the future?

Cloud computing and open-source software tools — which help models run faster — may come to workers’ comp sooner rather than later as companies compete more heavily on the strength of their analytics capabilities.

“Tools for unstructured data are also going to be big,” Anderson said. Currently much of the data collected comes in various formats —images, handwritten documents, emails, voicemails, etc. Tools capable of capturing and organizing this information will reduce the chance of error due to incomplete data.

Artificial intelligence platforms, in combination with unstructured data tools, may also be able to make and execute simple decisions by automatically generating new documents and records.

Predictive Models Provide Value in Workers’ Comp

Optum is helping to evolve the use of predictive analytics in workers’ comp. Thanks to its unique experience across the health system, working with providers, health plans, employers, government agencies and life sciences organizations, Optum is fluent in all of the types of data its clients use.

Its own predictive analytics platform, OptumIQ, brings together this data with advanced analytics and clinical expertise to better evaluate risk and drive more effective decision-making.

“We pull in more than just pharmacy data to create dynamic and constantly displayed risk score that will help adjusters or risk managers see how the patient is doing in real time,” Emptage said. “The need for intervention can be identified earlier, and predictive analytics helps us know where  potential risks are and even what our options may be.”

“We can uncover risk and guide action, which brings value to both our clients and injured workers,” Anderson said.

To learn more, visit http://www.workcompauto.optum.com/.

 SponsoredContent

BrandStudioLogo

This article was produced by the R&I Brand Studio, a unit of the advertising department of Risk & Insurance, in collaboration with Optum Workers’ Compensation and Auto No-Fault. The editorial staff of Risk & Insurance had no role in its preparation.




The Optum workers’ compensation and auto no-fault division works to collaborate with our clients to deliver value beyond transactional savings while helping ensure injured parties receive safe and effective clinical care throughout the life of their claim. Our innovative and comprehensive cost management programs include pharmacy care services, ancillary benefit management, medical services, and settlement solutions.

More from Risk & Insurance

More from Risk & Insurance

Risk Scenario

The Betrayal of Elizabeth

In this Risk Scenario, Risk & Insurance explores what might happen in the event a telemedicine or similar home health visit violates a patient's privacy. What consequences await when a young girl's tele visit goes viral?
By: | October 12, 2020
Risk Scenarios are created by Risk & Insurance editors along with leading industry partners. The hypothetical, yet realistic stories, showcase emerging risks that can result in significant losses if not properly addressed.

Disclaimer: The events depicted in this scenario are fictitious. Any similarity to any corporation or person, living or dead, is merely coincidental.

PART ONE: CRACKS IN THE FOUNDATION

Elizabeth Cunningham seemingly had it all. The daughter of two well-established professionals — her father was a personal injury attorney, her mother, also an attorney, had her own estate planning practice — she grew up in a house in Maryland horse country with lots of love and the financial security that can iron out at least some of life’s problems.

Tall, good-looking and talented, Elizabeth was moving through her junior year at the University of Pennsylvania in seemingly good order; check that, very good order, by all appearances.

Her pre-med grades were outstanding. Despite the heavy load of her course work, she’d even managed to place in the Penn Relays in the mile, in the spring of her sophomore season, in May of 2019.

But the winter of 2019/2020 brought challenges, challenges that festered below the surface, known only to her and a couple of close friends.

First came betrayal at the hands of her boyfriend, Tom, right around Thanksgiving. She saw a message pop up on his phone from Rebecca, a young woman she thought was their friend. As it turned out, Rebecca and Tom had been intimate together, and both seemed game to do it again.

Reeling, her holiday mood shattered and her relationship with Tom fractured, Elizabeth was beset by deep feelings of anxiety. As the winter gray became more dense and forbidding, the anxiety grew.

Fed up, she broke up with Tom just after Christmas. What looked like a promising start to 2020 now didn’t feel as joyous.

Right around the end of the year, she plucked a copy of her father’s New York Times from the table in his study. A budding physician, her eyes were drawn to a piece about an outbreak of a highly contagious virus in Wuhan, China.

“Sounds dreadful,” she said to herself.

Within three months, anxiety gnawed at Elizabeth daily as she sat cloistered in her family’s house in Bel Air, Maryland.

It didn’t help matters that her brother, Billy, a high school senior and a constant thorn in her side, was cloistered with her.

She felt like she was suffocating.

One night in early May, feeling shutdown and unable to bring herself to tell her parents about her true condition, Elizabeth reached out to her family physician for help.

Dr. Johnson had been Elizabeth’s doctor for a number of years and, being from a small town, Elizabeth had grown up and gone to school with Dr. Johnson’s son Evan. In fact, back in high school, Evan had asked Elizabeth out once. Not interested, Elizabeth had declined Evan’s advances and did not give this a second thought.

Dr. Johnson’s practice had recently been acquired by a Virginia-based hospital system, Medwell, so when Elizabeth called the office, she was first patched through to Medwell’s receptionist/scheduling service. Within 30 minutes, an online Telehealth consult had been arranged for her to speak directly with Dr. Johnson.

Due to the pandemic, Dr. Johnson called from the office in her home. The doctor was kind. She was practiced.

“So can you tell me what’s going on?” she said.

Elizabeth took a deep breath. She tried to fight what was happening. But she could not. Tears started streaming down her face.

“It’s just… It’s just…” she managed to stammer.

The doctor waited patiently. “It’s okay,” she said. “Just take your time.”

Elizabeth took a deep breath. “It’s like I can’t manage my own mind anymore. It’s nonstop. It won’t turn off…”

More tears streamed down her face.

Patiently, with compassion, the doctor walked Elizabeth through what she might be experiencing. The doctor recommended a follow-up with Medwell’s psychology department.

“Okay,” Elizabeth said, some semblance of relief passing through her.

Unbeknownst to Dr. Johnson, her office door had not been completely closed. During the telehealth call, Evan stopped by his mother’s office to ask her a question. Before knocking he overheard Elizabeth talking and decided to listen in.

PART TWO: BETRAYAL

As Elizabeth was finding the courage to open up to Dr. Johnson about her psychological condition, Evan was recording her with his smartphone through a crack in the doorway.

Spurred by who knows what — his attraction to her, his irritation at being rejected, the idleness of the COVID quarantine — it really didn’t matter. Evan posted his recording of Elizabeth to his Instagram feed.

#CantManageMyMind, #CrazyGirl, #HelpMeDoctorImBeautiful is just some of what followed.

Elizabeth and Evan were both well-liked and very well connected on social media. The posts, shares and reactions that followed Evan’s digital betrayal numbered in the hundreds. Each one of them a knife into the already troubled soul of Elizabeth Cunningham.

By noon of the following day, her well-connected father unleashed the dogs of war.

Rand Davis, the risk manager for the Medwell Health System, a 15-hospital health care company based in Alexandria, Virginia was just finishing lunch when he got a call from the company’s general counsel, Emily Vittorio.

“Yes?” Rand said. He and Emily were accustomed to being quick and blunt with each other. They didn’t have time for much else.

“I just picked up a notice of intent to sue from a personal injury attorney in Bel Air, Maryland. It seems his daughter was in a teleconference with one of our docs. She was experiencing anxiety, the daughter that is. The doctor’s son recorded the call and posted it to social media.”

“Great. Thanks, kid,” Rand said.

“His attorneys want to initiate a discovery dialogue on Monday,” Emily said.

It was Thursday. Rand’s dreams of slipping onto his fishing boat over the weekend evaporated, just like that. He closed his eyes and tilted his face up to the heavens.

Wasn’t it enough that he and the other members of the C-suite fought tooth and nail to keep thousands of people safe and treat them during the COVID-crisis?

He’d watched the explosion in the use of telemedicine with a mixture of awe and alarm. On the one hand, they were saving lives. On the other hand, they were opening themselves to exposures under the Health Insurance Portability and Accountability Act. He just knew it.

He and his colleagues tried to do the right thing. But what they were doing, overwhelmed as they were, was simply not enough.

PART THREE: FALLING DOMINOES

Within the space of two weeks, the torture suffered by Elizabeth Cunningham grew into a class action against Medwell.

In addition to the violation of her privacy, the investigation by Mr. Cunningham’s attorneys revealed the following:

Medwell’s telemedicine component, as needed and well-intended as it was, lacked a viable informed consent protocol.

The consultation with Elizabeth, and as it turned out, hundreds of additional patients in Maryland, Pennsylvania and West Virginia, violated telemedicine regulations in all three states.

Numerous practitioners in the system took part in teleconferences with patients in states in which they were not credentialed to provide that service.

Even if Evan hadn’t cracked open Dr. Johnson’s door and surreptitiously recorded her conversation with Elizabeth, the Medwell telehealth system was found to be insecure — yet another violation of HIPAA.

The amount sought in the class action was $100 million. In an era of social inflation, with jury awards that were once unthinkable becoming commonplace, Medwell was standing squarely in the crosshairs of a liability jury decision that was going to devour entire towers of its insurance program.

Adding another layer of certain pain to the equation was that the case would be heard in Baltimore, a jurisdiction where plaintiffs’ attorneys tended to dance out of courtrooms with millions in their pockets.

That fall, Rand sat with his broker on a call with a specialty insurer, talking about renewals of the group’s general liability, cyber and professional liability programs.

“Yeah, we were kind of hoping to keep the increases on all three at less than 25%,” the broker said breezily.

There was a long silence from the underwriters at the other end of the phone.

“To be honest, we’re borderline about being able to offer you any cover at all,” one of the lead underwriters said.

Rand just sat silently and waited for another shoe to drop.

“Well, what can you do?” the broker said, with hope draining from his voice.

The conversation that followed would propel Rand and his broker on the difficult, next to impossible path of trying to find coverage, with general liability underwriters in full retreat, professional liability underwriters looking for double digit increases and cyber underwriters asking very pointed questions about the health system’s risk management.

Elizabeth, a strong young woman with a good support network, would eventually recover from the damage done to her.

Medwell’s relationships with the insurance markets looked like it almost never would. &

Bar-Lessons-Learned---Partner's-Content-V1b

Risk & Insurance® partnered with Allied World to produce this scenario. Below are Allied World’s recommendations on how to prevent the losses presented in the scenario. This perspective is not an editorial opinion of Risk & Insurance.®.

The use of telehealth has exponentially accelerated with the advent of COVID-19. Few health care providers were prepared for this shift. Health care organizations should confirm that Telehealth coverage is included in their Medical Professional, General Liability and Cyber policies, and to what extent. Concerns around Telehealth focus on HIPAA compliance and the internal policies in place to meet the federal and state standards and best practices for privacy and quality care. As states open businesses and the crisis abates, will pre-COVID-19 telehealth policies and regulations once again be enforced?

Risk Management Considerations:

The same ethical and standard of care issues around caring for patients face-to-face in an office apply in telehealth settings:

  • maintain a strong patient-physician relationship;
  • protect patient privacy; and
  • seek the best possible outcome.

Telehealth can create challenges around “informed consent.” It is critical to inform patients of the potential benefits and risks of telehealth (including privacy and security), ensure the use of HIPAA compliant platforms and make sure there is a good level of understanding of the scope of telehealth. Providers must be aware of the regulatory and licensure requirements in the state where the patient is located, as well as those of the state in which they are licensed.

A professional and private environment should be maintained for patient privacy and confidentiality. Best practices must be in place and followed. Medical professionals who engage in telehealth should be fully trained in operating the technology. Patients must also be instructed in its use and provided instructions on what to do if there are technical difficulties.

This case study is for illustrative purposes only and is not intended to be a summary of, and does not in any way vary, the actual coverage available to a policyholder under any insurance policy. Actual coverage for specific claims will be determined by the actual policy language and will be based on the specific facts and circumstances of the claim. Consult your insurance advisors or legal counsel for guidance on your organization’s policies and coverage matters and other issues specific to your organization.

This information is provided as a general overview for agents and brokers. Coverage will be underwritten by an insurance subsidiary of Allied World Assurance Company Holdings, Ltd, a Fairfax company (“Allied World”). Such subsidiaries currently carry an A.M. Best rating of “A” (Excellent), a Moody’s rating of “A3” (Good) and a Standard & Poor’s rating of “A-” (Strong), as applicable. Coverage is offered only through licensed agents and brokers. Actual coverage may vary and is subject to policy language as issued. Coverage may not be available in all jurisdictions. Risk management services are provided or arranged through AWAC Services Company, a member company of Allied World. © 2020 Allied World Assurance Company Holdings, Ltd. All rights reserved.




Dan Reynolds is editor-in-chief of Risk & Insurance. He can be reached at [email protected]