Crystal ball not necessary: predictive analytics helps health systems reduce denials

By Pete Bekas

The idea of having a crystal ball to better understand what claims will be denied is an awesome concept. But one we can’t rely on. Thankfully, we have predictive analytics to take the place of a crystal ball. Predictive analytics can produce results quickly, effectively and accurately. Many health systems use predictive analytics to identify and mitigate claims denials before they occur.

Over the last 20 years ago, data science models have been used across many industries with great success. In the last decade, the financial industry, for example, used predictive models to help identify potentially fraudulent credit card charges to help reduce unauthorized transactions.

Healthcare, in general, has been slower to adopt predictive analytics, yet those healthcare organizations that do use analytics software report gains in productivity and cost savings. This is important because the cost to collect is generally one of the largest non-clinical related expenses for a health system. (Denied claims run into the hundreds of billions each year.) Unfortunately, there have been limited improvements over the last 10 years in how health systems manage the revenue cycle.

Nevertheless, health systems recognize the importance of improving the revenue cycle process. Every health system I work with has a dedicated team for denials. The amount of revenue leakage is just too great to not have people focused on these efforts. While determination to stem revenue leakage is commendable and necessary, predictive analytics can help providers process more claims more quickly and effectively. The outcome is fewer denied claims, which leads to improved revenue.

Reducing Costs While Reducing Denials

One of the most promising developments to help reduce the cost to collect is predictive denials powered by analytics. Leveraging the large amounts of data providers already possess, coupled with data science utilities such as R and Python, offer advanced health systems a glimpse into what the future of the revenue cycle holds. Predictive denials can help the health system reduce costs because of the software’s ability to quickly and automatically parse thousands of claims. This allows staff to focus on other revenue-generating projects.

The use of predictive denials, of course, won’t stop every denial. It will, however, help health systems avoid claims from being denied for specific reasons. There are many reasons payers deny claims, and predicative denials can help eliminate the most common.

Predictive denials help health systems mitigate issues with:

  • Questions about eligibility and gaps in benefits
  • Omitted patient identification and coverage information
  • Missing or invalid authorizations

The ability to correct claims before submitting them to payers alleviates many of the challenges involved with reworking claims. Additionally, it means health systems will receive cash more quickly, which drives down the cost to collect.

Although it would be great to have advanced models for predictive denials to cover all denials topics, payer rules and adjudication systems are constantly updated. Frequent modifications pose an ongoing struggle for health systems.

The best way to keep up is to use predictive denials that allow for both systematic and institutional learning, which has an immediate and long-term positive impact on managing denials and reducing the cost to collect. No crystal ball necessary.

Posted in

Product Consulting Team

With over 135 years of combined experience, the MedeAnalytics Product Consulting Team offers in-depth domain and product expertise to help payers and providers address their most significant analytics challenges and deliver measurable impact.

Leave a Comment





Get our take on industry trends

Data and Social Determinants of Health

December 19, 2019

By Scott Hampel – I think a lot–and I’m not the only one–about how we can improve the ways we pull information from data. Data on its own is inert: just waiting to be understood and then used. And that’s a major challenge for many organizations. Data is often trapped in different applications with no easy or convenient way to extract it.

Read on...

Why Social Determinants Need Analytics for Success

December 10, 2019

Many challenges face healthcare’s underserved. There are issues with food, housing, reliable transportation, steady employment and more. Each contributes to and is one element of social determinants of health (SDH). In communities around the world, public and private organizations are taking steps to address SDH-related issues and challenges that negatively impact healthcare.

Read on...

Healthcare Organizations Recognize Importance of AI for Reporting

November 21, 2019

Healthcare providers continue to recognize the value of using AI in reporting operations throughout the organization. AI has many strengths when applied to the healthcare industry:

Read on...

Why It’s Time for Healthcare to Move Toward AI Reporting

November 5, 2019

Business intelligence (BI) was a dramatic and significant step forward in healthcare industry reporting and a natural transition to artificial intelligence (AI) enabled real-time insights.

Read on...