Revenue leakage on the front end and mid-cycle is an ongoing challenge for hospitals and health systems. Rather than taking a reactive approach to the problem, proactively collaborating among teams prior to admission helps providers avoid playing the blame game when their claims are denied after the fact.
By focusing on reducing the number of denials before a claim is submitted, rather than trying to eliminate denials after the fact, revenue cycle managers can save time and energy. Today’s AI tools can help predict payer behavior, and by extension help utilization management teams differentiate between avoidable and unavoidable denials.
The blame game
Accurately discerning unavoidable and avoidable claims denials — on the front end, before they are submitted — can potentially save time, effort, and money for many stakeholders. When time is scarce and every dollar is scrutinized, any time spent on claims that are denied a high percentage of the time amounts to a waste of time for UM (utilization management) teams.
Without knowing a denial was unavoidable (with a high degree of accuracy, at least), revenue cycle managers might be led to play the “blame game” on the back end. Why wasn’t a claim approved? The answer might be as simple as “it had a very low chance of approval from the start” regardless of who handled it along the way.
Differentiating between avoidable and unavoidable denials is easier said than done. Payer medical policy, and payer medical necessity, are not the same thing. Some claims might not be submitted simply because the UM team doesn’t believe it will be approved — even though the data says it has a chance. And a robust data set is harder to argue with than an individual’s instincts.
AI and data: the future of best practices
Today’s AI tools can draw on thousands of historical data points to identify patterns, like how often a similar claim is denied or approved. This data can inform stakeholders about what to expect prior to admission. Historical payment rates by payer, by financial class, by the age of the account, and other data offers a more objective, specific way to mitigate denials on the front end of the revenue cycle.
This data is not only useful to UM staff, but to any hospital or health system’s CFO, finance leaders, and physician advisors about likely denials and missed inpatient conversion opportunities. These stakeholders can identify trends specific to the front end of the revenue cycle, comparing denials issued depending on the nurse, doctor and payer for the same medical condition.
That’s a high volume of data, with plenty of ways to slice it up. Fortunately, AI-based inpatient prediction tools can streamline the process of large data analysis for UM teams.
By using AI-based inpatient prediction tools to discern the risk of denials proactively, providers can mitigate a number of common revenue integrity problems. By providing a more objective, specific way to measure the likelihood of denial, this cutting-edge analysis saves time and can prevent the “blame game” before it even starts.
About Tanya Sanderson
Tanya Sanderson is the Senior Director of Revenue Integrity with Xsolis, the AI-driven health technology company with a human-centered approach. Tanya’s healthcare career spans 30 years including clinical nursing, legal and regulatory consulting, and healthcare revenue cycle. For more than a decade, Tanya has built and transformed revenue integrity and denial management teams and created processes to improve denial mitigation, revenue recovery, and revenue compliance in multiple settings ranging from 12-hospital centralized business offices to enterprise oversight in $14+ billion integrated health systems.
