Some experts estimate that $200 billion is wasted each year on unnecessary or excessive medical testing and treatment. This could be up to 40% of the unnecessary spending in the system today.
Despite the extreme focus to reduce the total amount spent on healthcare, why does extensive spending on unnecessary or excessive tests or procedures continue? The easy answer is because it is often difficult to spot what is unnecessary or excessive.
There are certainly moments when overutilization of the system for unnecessary tests can be pinpointed to a specific cause. A few years ago, for example, Angelina Jolie’s double mastectomy prompted a massive spike in BRCA tests, including among a significant number of women who had a low probability of carrying the mutation. While this type of overutilization may not be predictable, it is also not the main culprit of overspending.
Recognizing Wasteful Patterns
Want to publish your own articles on DistilINFO Publications?
Send us an email, we will get in touch with you.
Instead, there is more subtle overutilization that can be from provider behaviors or from individual patients. But this type of waste is rarely detected because of the way that payment integrity is currently conducted. Today, most payment integrity programs include some automation but also a significant amount of manual work to verify the payment, identify potential fraud or misuse, and acknowledge patterns or anomalies. The complexity and variety of claims apart from medical, such as imaging, pharmacy and behavioral, increases the challenge.
With the continued increase in claims and general skyrocketing of the amount of data, it would be difficult at best to recognize patterns and correct them for the future. However, with the recent advances in technology, health plans have an opportunity to build a better payment integrity system using artificial intelligence (AI).
AI, if applied correctly, has the potential to become a reliable, efficient and cost-effective solution to mitigate improper claims payments that cost the system billions of dollars each year. AI can detect patterns and anomalies in seconds instead of days or weeks to help plans reduce current and potential future waste, fraud, and abuse of the system. By effectively utilizing AI, health plans can decrease unnecessary spending, but also educate providers so all parties can collaborate on high-quality, evidence-based care alternatives.
Payment Integrity and AI
Payment integrity is by no means a new concept. Ensuring an accurate, contracted reimbursement for medical and related services is as old as the third-party payment model in healthcare. As new tests and services are innovated and patients become more numerous and complex, it is growing harder for payers to determine what is a medically necessary test or service and which is not. The volume of claims also makes it more difficult to detect coding error trends, documentation problems, and outright fraud.
With AI, identifying medical necessity, as well as fraud and errors, can be faster and more precise. Leading AI technology that supports pre-pay reviewer staff, for example, can rapidly identify a potentially improper payment before a claim is paid due to the technology’s pattern recognition that learns the more it is utilized. By reviewing claims this way, health plans can avoid payment errors related to Diagnosis Related Group (DRG) coding and validation, readmissions, level of care, place of service, and more, which saves time and burden trying to recoup payment.
With algorithms created with thousands of data points, AI and machine learning technologies can keep edits refreshed to identify emerging improper payment trends and target claims with the highest potential for fraud. That means the administrative burden is further reduced because medical records are only requested when there is a likely improper payment, saving time for all stakeholders involved. These edits extend across all claim types and billing issues, too.
Furthermore, AI combined with natural language processing (NLP) and other technologies improves efficiencies and ensures low amounts of false positives, reducing unnecessary work for payers and providers. NLP, in particular, can review medical records in a fraction of the time of manual reviews while robotic processing enhances efficiency by automating critical paths that are typically triggered by human intervention.
McKinsey estimates that payers can save as much as 10% to 20% of medical costs if they use advanced data analytics for just a portion of the claims management steps, such as to identify claims that are likely overpaid or fraudulent. That savings can climb to 30% or more if payers can automate most of the claims management process, according to McKinsey.
Educating Providers
Yet perhaps the largest impact that AI can bring to preventing overutilization and errors is to help providers detect it before the service is performed or claim is submitted. During the appeal or overpayment recovery process, health plans can educate providers about the errors, non-compliance or why the test or service was rejected or overpaid using data pulled from analytics as evidence. Such education can lead to increased provider cooperation and result in fewer appeals.
Similarly, when a test or service is ordered, AI technology on the provider side can analyze the vast amount of data available to notify the physician if the care may be deemed medically unnecessary by that particular health plan and list the factors that may cause a claim denial.
Ensuring maximum cost containment and program efficiency requires payment integrity solutions be deployed across the healthcare continuum—from pre-service through post payment. Adding leading technologies such as AI, machine learning, NLP and robotic processing give payers an advantage at controlling their spending while helping providers better manage their revenue cycle so they have fewer denials and appeals and overall more predictable cash flow.
Source: HIT Consultant
