Fill form to unlock content
Error - something went wrong!
Please complete this brief form to read this eBook.
Thank you!
How to evolve your FWA program in 2025
Ryan Cleverly, AHFI and Vince Smith, AHFI, CFE
Fraud, waste, and abuse (FWA) in healthcare can significantly increase costs and adversely affect quality of care. The extent of FWA in healthcare is staggering, with an estimated 25% of total healthcare spending in the U.S. considered wasteful, and as much as 10% considered fraudulent.
As the annual rate of healthcare spending in the United States soars beyond $4.9 trillion, the financial impact of FWA also increases, amounting to hundreds of billions of dollars each year. This not only inflates healthcare premiums but also strains resources and undermines trust in healthcare institutions. Addressing FWA effectively is imperative to streamline healthcare operations and reduce unnecessary expenditures.
In this eBook, we offer insight into common challenges with long-standing approaches to FWA management, and explain how payers can deploy technological advancements and machine learning alongside human expertise to reduce FWA.
Table of contents
Challenges faced by today’s health plan SIUs
Constructing a new approach to FWA management
Deploying advanced tools and technologies
Challenges faced by today’s health plan SIUs
Traditional methods of managing FWA often rely on manual processes and outdated tools that are unequipped to handle the complexity of modern healthcare systems and the scale of data. These methods generally involve identifying fraudulent activities through manual claims data analysis and provider audits. This makes it difficult to promptly detect sophisticated schemes and manage large amounts of data without the proper scope of resources, often resulting in overworked special investigation units (SIUs).
SIUs within healthcare organizations are often tasked with combating FWA. In Cotiviti’s experience, many SIUs face considerable resource constraints. They are often understaffed and lack the necessary tools and technology to conduct thorough investigations. SIUs that are overloaded or have limited resources struggle to address the volume and complexity of FWA cases effectively.
Traditional methods of managing FWA often rely on manual processes and outdated tools that are unequipped to handle the complexity of modern healthcare systems and the scale of data.
For example, traditional FWA management software frequently generates large amounts of data that requires extensive manual analysis, leading to delays and missed opportunities for early intervention. Investigators may spend significant time exporting all the claims data and performing manual spreadsheet analysis outside their software, only to find that many leads are false positives.
False positives are a major issue in traditional FWA management, causing investigators to spend valuable time chasing leads that ultimately prove unproductive. This not only wastes resources, but allows truly fraudulent activities to remain undetected, thus making the case for a more accurate and efficient system that can nullify false positives and save time.
Constructing a new approach to FWA management
The evolving landscape of healthcare demands a new approach to FWA management that leverages advanced technologies, innovative strategies, and human expertise. The introduction of artificial intelligence (AI) and machine learning into the healthcare payment space offers several benefits, including enhanced accuracy, efficiency, and scalability.
For example, Cotiviti’s 360 Pattern Review solution, which combines prepay and postpay capabilities, provides vetted leads and full-service investigations, backed by a team of highly trained specialists, helping to significantly reduce the burden of work for SIUs. This system generates "lead packages" which include detailed analysis and recommendations, enabling investigators to focus on the most promising cases, minimizing wasted effort and maximizing the effectiveness of FWA investigations.
The introduction of AI and machine learning into the healthcare payment space offers several benefits, including enhanced accuracy, efficiency, and scalability.
Collaboration between prepay and postpay teams is also crucial for effective FWA management. Having a team of experts who are educated and certified in medical and dental coding, chart auditing, FWA investigation, and pharmacy can help identify evolving schemes. By facilitating seamless communication and coordination between these teams, investigators gain more confidence that fraudulent activities are detected and addressed promptly, enabling a shift from recovering inappropriate payments to preventing them in the first place while enhancing overall performance.
Deploying advanced tools and technologies
Effective case management is essential for successful FWA investigations. Using an advanced case management tool specifically designed for SIUs can help streamline the process of tracking, reporting, and managing cases, which in turn stops abusive or fraudulent practices before they evolve. These tools include configurable dashboards and real-time updates that enhance visibility and control while providing a clear and seamless way to track an investigation from start to finish.
Machine learning has the potential to revitalize FWA management by enabling the detection of complex fraud schemes and patterns that traditional methods, such as purely rules-based engines, typically can’t catch. While rules-based engines can identify well-known, black-and-white schemes, by identifying anomalies just as they begin to occur, machine learning can aid with early intervention for more complex schemes, rank providers based on potential risk, and help prioritize efforts more effectively, alleviating the burden of data overload often faced by SIUs.
Designed with user friendliness in mind, tools like 360 Pattern Review help ensure that investigators can easily navigate and utilize advanced technologies without extensive training. This application is built to be user-friendly compared to legacy systems, with features such as hover-over tips and consolidated functionalities that save time and reduce complexity.
Machine learning can aid with early intervention for more complex schemes, rank providers based on potential risk, and help prioritize efforts more effectively, alleviating the burden of data overload often faced by SIUs.
The value of a managed service model
Despite the challenges of legacy FWA software systems, many health plans are hesitant to disrupt the status quo because of how cumbersome replacing these systems can be, causing even more stress for an already-burdened SIU. While newer, more advanced software may offer more promising features, it also can be both time-consuming and expensive to maintain, depending on the vendor’s level of support.
This is where a managed service model—wherein the health plan’s vendor vets and delivers leads, provides ongoing maintenance and updates, and offers customized support—can be particularly useful for SIUs with limited resources. Rather than requiring the health plan to displace its current systems, the vendor can work with the plan to deploy the new solution alongside its existing systems, augmenting the SIU’s current software and processes while delivering new value.
Real-world applications and takeaways
One health plan approached Cotiviti seeking help monitoring claim volume for patterns of improper billing before claims payment, emphasizing the importance of not causing additional work for the SIU team to vet leads, implementing AI-driven Claim Pattern Review to prevent inappropriate payments without increasing appeals. Another plan also implemented Claim Pattern Review to leverage the power of advanced FWA analytics, pattern recognition, and machine learning alongside Cotiviti’s prepay claim editing and clinical coding review solutions. Across all clients, Cotiviti’s FWA approach and team identified more than $15 billion in suspect claims in a single year.
The evolving world of FWA schemes emphasizes the importance of leveraging advanced technologies, fostering collaboration between teams, and continuously refining processes to adapt to emerging challenges. Utilizing machine learning in payment integrity can benefit investigative accuracy and identify potential schemes sooner, when it matters most.
Across all clients, Cotiviti’s FWA approach and team identified more than $15 billion in suspect claims in a single year.
Fraud, waste, and abuse in healthcare remains a critical issue that demands innovative solutions and a comprehensive and effective strategy that meets the goals set by an organization. By leveraging advanced tools and technologies to enhance accuracy, efficiency, and collaboration with a new approach, health plans can significantly reduce costs, improve service delivery, and help ensure a more sustainable and equitable healthcare system for their members.
Now, put what you’ve learned in this eBook into action and learn more about 360 Pattern Review: an unmatched combination of Cotiviti’s proven prepay Claim Pattern Review and the brand-new postpay FWA Pattern Review.
Watch our on-demand webinar to learn how 360 Pattern Review empowers your SIU to:
- Deliver rapid ROI through automated detection
- Identify potential FWA earlier
- Eliminate wasted time spent on false-positive leads
- Boost staff productivity
Don’t miss this opportunity to join the evolution and take your FWA programs to the next level.
About the authors
|
Ryan Cleverly, AHFI Ryan is responsible for the strategic direction of Cotiviti’s FWA product offerings, including both postpay and prepay FWA detection. Previously, Ryan worked as a criminal investigator investigating allegations of all types of insurance fraud including healthcare and pharmaceutical fraud. Ryan also worked on a Federal Healthcare Task Force focused on provider fraud and conducted multiple complex healthcare investigations. |
![]() |
Vince Smith, AHFI, CFE Vince is responsible for analyzing and interpreting claims data to identify potential FWA, conducting extensive fraud investigations on behalf of private insurers, and assisting with the recovery efforts for schemes identified with the investigations. Prior to joining Cotiviti, he was a contracted senior compliance auditor for CMS and worked with the Division of Compliance Enforcement (DCE) to identify fraud and non-compliance occurring within federally funded health plans. |