Getting paid is essential to practice success.
Making sure your practice gets paid correctly is one of the most important priorities of any practice leader. In the current healthcare space, 30% of medical practices are closing just this year, and everyone else is struggling to remain financially viable. On top of this, CMS continues to cut physician reimbursement by 3-4% every year despite rising inflation and practice expenses. This isn’t sustainable without making sure every dollar owed is collected.
The problem – there is a data gap, and insurance companies are winning.
Getting paid for healthcare services performed has become exceedingly complex. Between making sure documentation is complete, ensuring compliance with ICD10 and CPT coding rules, monitoring numerous claims and remittances, and keeping up with constantly changing insurance plans – it’s an impossible task to track whether insurance companies and patients have paid for the services provided. Insurance companies know this – and are taking advantage of it.
A recent government audit found that privately-run Medicare Advantage plans don’t pay for almost 20% of claims that CMS mandates they should. Likewise, Cigna has built AI-technology to ‘auto-deny’ claims under medical review every 1.2 seconds. The American Medical Association estimates that practices are leaving 10-20% of their annual revenue behind in non-payment. United Healthcare just got fined $150 million dollars in federal court for not paying what they owed practices. And yet, empowered by sophisticated AI technology, healthcare payers are making billions of dollars a year in profit.
The solution – Use advanced AI-driven revenue cycle management analytics in your practice. Immediately.
Practices are inundated with reimbursement data – from patient and service data, to initial claims, insurance remittances, and payment data. Yet, deploying advanced AI analytics can be yield immediate financial results – from identifying common payment errors; denials from claim errors; and variable payment behavior for standard services. Many of the data fusion and AI surveillance tools that some platforms deploy were developed in much more data intensive industries (think military or industrial engineering) and are now being leveraged effectively to track insurer payment errors.
Here is a step-wise approach to successfully incorporating AI-driven analytics into your revenue cycle team:
Step 1. Find the optimal AI platform for you. Most data analysis packages available to practice managers are ancient – not designed to handle the mountains of complex data that current healthcare reimbursement processes throw at them. On top of that, analytics tools embedded in legacy EHR or practice management software aren’t intuitive, and don’t automatically call out payment errors. Newer systems often force practices to ‘rip-and-replace’ their billing or EHR software, making them costly and high-risk to implement.
Optimal next-generation AI data platforms should be vendor-agnostic; able to seamlessly integrate with any practice system. They should also be able to handle large amounts of data from multiple sources; fusing different data sets to correct for the industry-expected 30-40% error rate between practice data sources. Practices need this data to be available in near real-time to position their billing teams and practice managers for fast-response times – which correlate directly to higher payment rates.
Finally – the AI system needs to bring the critical information to you, rather than forcing you to dig constantly. This levels the playing field – with practice re-focusing critical staff on collecting revenue from payers rather than sifting through data. The best defense is a good offense.
Step 2. Focus on high-yield practice revenue gaps. Once practices have a powerful AI data platform at their disposal, they can tackle several key areas for financial gain immediately – either through reclaiming unpaid revenue or working to prevent non-payment for services moving forward. The first focus is on services that are being denied due to lack of insurance pre-authorization approvals or are non-covered services by particular payers or plans.
Practices that have high value services (such as drug infusions, surgeries, or procedures) can also track the subset of claims that have individual values above a certain threshold – as these are often sub-categories that insurers underpay. Patient co-payments are also an area of underappreciated financial loss that can be improved through implementation of simple front-desk protocols.
Finally, the most state-of-the-art data platforms can track insurer underpayment, identifying claims that have been paid less or denied compared to what a practice should expect based on their own historical data, contracted rates, or Medicare benchmarks. This is where the real opportunity lies – in uncovering where insurance companies are unfairly denying you.
Step 3. Figure out what you can focus on and how to re-prioritize your staff. When a new and all-powerful AI data platform is deployed in a revenue cycle team, the results can be overwhelming. Suddenly, staff who spent days and weeks assembling data are now freed up to take action. Those practices that gain the most out of AI revenue surveillance do so by quickly identifying where the most financial opportunity is (e.g. highest-value for lowest effort) and focus on solving that issue, before moving on to the next best opportunity. As the old adage goes, “How does one eat an elephant? One bite at a time.” Can you take advantage?
This is where MicroMD comes in. We’ve partnered with RevOps Health to make their next generation AI-driven revenue cycle management data platform available to track down when insurances aren’t paying our customers properly.
Their team of engineers, data scientists, and healthcare professionals knows exactly where to look – and are making it so that it takes your team just a few minutes to catch insurers in the act. Are you AI-ready to take back control of your revenue data? Let us help you.
