3 Ways to Leverage Big Data for Better Statement Processing Results

September 23, 2014 Brian Watson

Use big data and predictive analytics to improve statement processing performanceBig data has quickly become one of those catchall technology buzzwords – like cloud computing or gameification – that’s thrown around incessantly these days.

And it’s not hard to see why.  There’s just something so cool and mysterious about what the term implies: quickly mining huge data sets to uncover actionable information to solve big problems. 

But big data isn’t a new concept for the healthcare industry.   

For years, providers have been at the forefront of the trend – pushing the envelope on how large sets of scientific evidence can be used to improve clinical outcomes.  Or improve the effectiveness of triage in an immediate care setting.  Or drill down to the root causes of preventable hospital readmissions. 

What is new is that big data trend is beginning to spread from the treatment environment to the business office and operational side of things.  Now COOs and Patient Accounts Directors are starting to get in on the fun.

Armed with better, faster, smarter technology and an EMR- and Affordable Care Act-aided push for greater transparency, providers are tapping into data and analytics to solve really-big operations issues like never before.

For example: a hospital using aggregate financial data to develop propensity to pay models to get more patients at financial risk signed up for charity care, or on a sensible payment plan, or access to financial counseling at the right time.

Or a clinic using data on patients’ buying habits and preferences to provide more personalized, effective marketing outreach.

Combing Clinical and Financial Analytics for Better Patient Outcomes

Operations-centric big data applications – like revenue cycle analytics – might not grab headlines like some of the data mining and digital pathology breakthroughs on the clinical side.  But that doesn’t mean they’re any less important to the future of healthcare.

Not with the continued growth in healthcare spending.  By 2021, The Center for Medicare and Medicaid Services estimates costs of care in the U.S. will reach $4.8 trillion, nearly doubling the $2.6 trillion spent in 2011.  If that forecast proves accurate, it will represent a full one-fifth of the U.S. economy.

In the face of rising expenditures, patients need better, more efficient care and a financial process that’s fast, fair, and easy to understand.

That means intertwining clinical and operational analytics.  Big data can help doctors provide more personalized, effective care.  It can help patients monitor and improve their own health.  And it can help the entire process cost a whole lot less and be much easier for patients to understand and pay for.

What are some of the low-cost applications providers are tapping into to improve patient outcomes and revenue cycle operations?

Propensity-to-Pay Analytics

As the revenue cycle continues to evolve from post- to pre-service, providers are becoming more proactive in how they approach patient financial operations.

Perhaps the most important first step providers can take in developing a forward-thinking patient financial strategy is establishing propensity-to-pay analytics. 

Providers are now turning to analytics to develop a robust patient financial profile that can be used for a number of efficiency-boosting business office applications.  The best self-pay predictive models integrate external information – like credit score, federal poverty level, marital and employment status, and ZIP code – with proprietary data like payment history, balance owed, and balance paid.  Once established, these propensity-to-pay metrics can be leveraged to:

• Intelligently Segment Patients Into More Efficient Self-Pay Collection Silos

Instead of using receivables aging or amount owed, predictive modeling enables providers to group patients into like segments for customized, outcome-driven financial outreach. 

For example, a patient segment with a high outstanding balance and low propensity-to-pay score would receive additional attention that might include pre-service financial counseling, proactive enrollment in a payment plan, or transfer to an early-out program.  On the other hand, patients that fall into categories with a stronger propensity to pay score would be entered into a more traditional billing program with follow-up from your staff.

Not only does this approach provider a smarter allocation of employee productivity, it also improves collectability and patient satisfaction by presenting a clear accounting of the patient’s financial responsibility and a roadmap to ensure payment.

• Develop Tailored Payment Options

A holistic snapshot that includes financial history, propensity-to-pay modeling, and account status across the entire health system makes it much easier – and faster – for healthcare organizations to craft fair, effective payment plans for patients.

Custom algorithms can be used to uncover patients that meet guidelines for financial hardship, but don’t qualify for Medicaid or similar charity care, before they contact you requesting financial assistance – or even leave your facility.

That’s significant When coupled with tiered payment plans, the data becomes actionable.

For example, a low propensity-to-pay score on a high balance could prompt pre-discharge financial counseling or a mailing of a financial aid letter and application.  While a slightly higher score on a balance due of less than $2,000 automatically triggers a proposed payment plan with specific terms to fit the patient’s financial profile to be added to their statement. 

Charity Care Screening

Whether it’s because patients are daunted by the application process or unsure if they qualify, most hospitals write off as bad debt revenue that might otherwise qualify as charity care under state and federal poverty guidelines.

That’s why many providers are leveraging financial data to screen for eligibility with Medicaid and related charity care programs.  Algorithms that incorporate elements like credit score, propensity to pay data, payment history, and family size are used to develop a charity care estimate for patients.  That’s commonly coupled with an internal assessment of payment data to determine the level of financial hardship that typically correlates with non-payment.

Charity care metrics can be used reactively – during financial counseling after eligibility is determined but prior to treatment, or when a patient calls in for financial assistance.  Or presumptively – as an analytical tool to assess accounts that have passed through first and second placements without payment or a request for financial assistance.

Analytical charity care screening helps move the application burden from patient to provider – reducing the chance that qualifying balances fall through the cracks and become bad debt.

Patient Statement Split Testing

Yes, even something as tried-and-true as statement processing is receiving an analytical makeover these days.

But what does big data have to do with ink-on-paper statements?  In a word: effectiveness. 

Healthcare organizations have long understood the inherent value in patient friendly statement design.  As the primary communication vehicle for self-pay payment, smart, well-designed statements still have considerable bottom-line significance to providers.  They reduce operational costs.  Provide relief to overburdened business offices.  And – most importantly – speed collectability.

That explains the industry-wide pursuit of patient-friendly, best-practice statement design.  But while the gains from something like a full-scale redesign are relatively easy to track against receivables, too often incremental improvements – the minor upgrades and changes that happen frequently – go by unverified.

Did that revised coupon change really reduce payment issues?  Is the new FAQ limiting service center calls?  Revenue cycle performance is too important to trust statement changes to a gut feeling or anecdotal evidence.

That’s why providers are now mining analytical data to answer the critical statement usability questions that affect organizational profitability.

• A/B Split Testing

Structured design experiments enable healthcare organizations to closely track and monitor the success of individual statement changes.  Key performance indicators are analyzed pre- and post-change to identify trends in relevant revenue cycle data.

Elements that outperform the control group in an experiment are integrated into an organization’s statement, while those that demonstrate little or a negative impact don’t become part of the “winning” or control statement.  Over time, this approach provides healthcare organizations with a proven, best-practice statement that resonates specifically with their patient base.

• Design Analytics

A/B split testing delivers actionable statement design insights.  But it’s also a painstaking process.

Fortunately, statement processing companies are in a unique position to accelerate the process with statement design analytics.  What’s the secret sauce?  In a word: scale. 

Instead of a single healthcare organization running a few split tests each year a statement processing vendor might have access to usability scenarios and efficacy data from their entire customer database. That could means upwards of hundreds or thousands of hospital and clinics, each taking part in several design experiments each year.

It’s not hard to see how that volume, tracked appropriately, could quickly provide a statement print and mail best-practices database from which providers seeking a specific result – say lower call volume logged by patient service representatives, or more patients making a payment using an online channel – can tap into.

By leveraging the wisdom of the crowd, statement processing companies can help providers eliminate the guesswork and tediousness of best-practice statement design – immediately arming you with a document that’s proven to pay dividends.

Statement Design Consultation

Share This: