Healthcare Analytics is Crucial for Employee Benefits—Here’s Why

Healthcare analytics is a broad term that’s difficult to define. It could refer to a hospital using data to track patient outcomes. It could also apply to a health insurance carrier mining healthcare claims data to determine which hospital systems should be in their network. Even a healthcare policy think tank may use healthcare data to track patient behaviors.

At Artemis, we know that healthcare analytics is increasingly a crucial part of any sound employee benefits strategy. Employers are using healthcare data to plan, measure and improve employee health benefits. 

So what is healthcare analytics? Broadly speaking, it’s the practice of using vast amounts of varied health data to inform best practices in healthcare. The University of Chicago Health Informatics department explains, 

“In the context of the health care system, which is increasingly data-reliant, data analytics can help derive insights on systemic wastes of resources, can track individual practitioner performance, and can even track the health of populations and identify people at risk for chronic diseases. With this information, the health system can more efficiently allocate resources in order to maximize revenue, population health and — very importantly — patient care.”

Healthcare data comes from many different sources, and can be used in a number of ways. For example, a hospital system would use healthcare analytics techniques to track: 

• Hospital admission and readmission rates 
• Costs for common procedures 
• Length of hospital stays 
• ER visits by condition 
• Patient outcomes 
• Supply needs for the hospital 
• Provider quality 
  

And that’s just to name a few. Employers are also using healthcare analytics to help control the cost of healthcare coverage they provide for employees and their families. Self-insured employers, those taking on the financial risk of healthcare claims incurred by members on their plan, are utilizing healthcare data to help their members access great care at a lower cost. Many self-insured employers are keeping an eye on key metrics that are similar but distinct from those used by hospitals. The healthcare data they’re collecting and analyzing might include: 

• High cost claimants in their population 
• ER utilization 
• Telemedicine benefit utilization 
• Health risk scores 
• Conditions by office location 
• Employee engagement in wellness programs 
• Provider quality 
• Costs for common procedures 
• Top conditions in their population 
  

And many more. Healthcare data analytics is a growing tactic used by employers to ensure that employees have a good experience with the healthcare system. They want to direct patients to the right point of service (e.g. ER vs. instacare, PCP vs specialist, etc.). They want to keep the rising cost of healthcare under control so they can continue to offer good coverage. And they want to offer other benefit programs that attract and retain talented employees. 

The goals of healthcare analytics are aligned between health systems and employers. As we’ve written about on the Artemis blog, there are a number of benefits to cooperation on data sharing between hospitals and self-insured companies. Data analytics leads to better health outcomes, price transparency, and the mutual ability to predict future costs. 

Above all, healthcare analytics can increase patient satisfaction. Patients are happier and healthier when they get the right diagnosis, are successfully treated, and pay what they expect to pay. 

On the employee benefits side, patients are employees. Having a good experience with employer-provided healthcare means that employees will be healthier, more productive, and more engaged with their healthcare benefits. Healthcare analytics can lead to a boost in employee satisfaction. 

In short, healthcare analytics can be a great bridge between employee health and employee satisfaction. But healthcare is just one part of the world of employee benefits. Why is healthcare analytics helpful for other employee benefit programs? How else is data analytics being used as a tool by HR and Benefits leaders? 

Healthcare analytics offers a holistic view. 

Health and wellness can’t be determined with a single claim or one data source. Imagine you’re an avid runner in excellent cardiovascular health who is seeking care for a knee injury. Someone looking just at your last few medical claims might think, “This person is a high cost claimant due to musculoskeletal issues.” But if they’d looked at healthcare data, biometrics data, wellness program participation, and more, they would know that the knee injury is just one piece of the puzzle. 

This holistic view is critical when using healthcare analytics for employee benefits. According to Willis Towers Watson’s annual Best Practices in Health Care Employer Survey, the most successful benefits leaders are using a benefits data warehouse to help them achieve a holistic view. A great health analytics platform will allow for unlimited data sources and enable the user to “crosswalk” or look across feeds to find health data insights. 

Here’s how it worked for one Artemis client. This employer’s consultant noted high absenteeism in their data, and decided to investigate further. Working with Artemis, we correlated behavioral health diagnoses (depression and anxiety) to absentee hours. This gave the employer the ammo needed to justify adding a behavioral health wellness program to help meet the needs of employees. 

The next step for this client and their consultant is to track participation and engagement with the new program to ensure it’s effective for these members. Healthcare data is essential for this process. 

Healthcare analytics identifies opportunities. 

It’s not just about mining data to find out how things are working. A good healthcare analytics strategy for employers should include a plan for finding opportunities for improvement. That’s where a benefits data warehouse can really shine. The best health analytics platforms will include proprietary tools and models to surface insights so the user doesn’t have to dig. 

Here’s an example. One of the many ways pharmaceutical companies are innovating is by combining two drugs into one pill. These “combination drugs” are convenient for patients and allow drug makers to apply for new patents, a win-win in their eyes. But it’s definitely not a win for self-insured employers or patients. These drugs can be more expensive than over-the-counter options or tablets that can be prescribed and taken separately. 

Artemis Chief Clinical Officer Rance Hutchings developed proprietary data models and used our health analytics solution to help a client identify combination drugs in their prescription claims data. This analysis focused on a name-brand NSAID-Antacid combination. NSAIDs are common pain medications (it stands for “non-steroidal anti-inflammation drugs”); ibuprofen and aspirin both fall into this category. Antacids treat heartburn and acid reflux, and many are taken daily. 

Here’s what we found:

Over a 1-year period, the employer paid $173,019 for this combination. That’s for a maximum of 18 members taking the drug. Through formulary adjustments, this client could change their coverage so these members are taking generic omeprazole and naproxen for an estimated savings of $75,000 per year. 

This definitely isn’t “big data”—we’re talking about Rx claims for less than 50 people. But this health data analysis identified an opportunity that the employer otherwise wouldn’t have found. 

Healthcare analytics can help predict the future. 

You’ve probably heard a lot about predictive analytics recently. It’s a trendy term that’s still somewhat undefined, but it generally means that data analytics can help predict the future. For hospitals that might mean the future of patient diagnoses, using data models to parse symptoms, compare them to population data, and identify the condition. For employers, it’s mostly about predicting future costs for budgeting. 

Risk scores are a good example. A risk score is a way to determine an individual member’s overall health. Each person’s risk score is based on their demographics, health status, and potential healthcare utilization. For example, someone with a high risk score may have a new diabetes diagnosis, while someone with a low risk score may have seen the doctor for the occasional seasonal cold. When analyzed on a population level, risk scores can help employers assess the potential future health of their population, and even be used to predict future healthcare spending.

In this analysis we did for a client, we separated out members by risk score, then narrowed in on diagnosis codes for just the high risk members. Using the claims paid amounts for those diagnoses, we’ve arrived at predicted cost ranges for these members:

A robust data warehouse solution can help employer benefits teams predict costs based on risk score and plan accordingly. 

So you can see why healthcare analytics is crucial not just for hospitals and health systems, but also for employee benefits. Employers want what’s best for their employees and their families, they’re using healthcare data to get a holistic view, identify opportunities, and predict the future.