Skip to main content
Hallway of a server room

AI Strategies to Help Combat Fraud, Waste, & Abuse in Healthcare

Learn how AI can help streamline authorization systems and proactively prevent losses.

As healthcare organizations strive to reduce costs and improve affordability and access to care, efficiently combating fraud, waste, and abuse (FWA) is an important goal. Prior efforts to identify and prevent FWA have often fallen short. However, new tools that harness the power of artificial intelligence (AI) can help streamline authorization systems, enhance access to evidence-based care, and proactively prevent losses due to FWA. Below, we explore how AI tools can help improve an organization’s anti-FWA strategy and how to implement these tools safely with human oversight.

The Five Pillars of Combating Fraud, Waste, & Abuse

An effective anti-FWA program comprises five pillars:

  1. Prevention: Proactively combating FWA with regular training, routine audits, data monitoring, and clear policies and procedures.
  2. Detection: Identifying and bringing attention to instances of FWA using strategies including data analytics and cross-verification.
  3. Investigation: Uncovering the details of detected FWA through audits, reviews, interviews, and interrogations; collaborating with law enforcement; and maintaining protections for whistleblowers.
  4. Reporting: Notifying the appropriate authorities through the proper channels, including state agencies, local law enforcement officials, and the Office of Inspector General.
  5. Mitigation: Responding to FWA incidents to reduce recurrences, using strategies including fraud risk assessments, newly developed or updated policies, training and awareness programs, and internal controls.

Historically, preventing FWA has relied on training, education, sound documented policies, and routine monitoring practices. While these methods have proved successful at identifying FWA, they have not been as effective at preventing losses related to FWA. Payors have typically relied on claims data analytics to identify outliers within a given look-back period, which often left them monitoring these outliers over months or even years before they could make credible allegations of FWA against a provider or member. As a result, the fraudulent, wasteful, or abusive patterns could continue for an extended period, driving up the costs of healthcare in the meantime.

Using AI to Improve Your Anti-FWA Strategy

Recent advances in AI have made it an effective tool to enhance all five pillars of an anti-FWA program. By harnessing the power of AI and advancing interoperability between disparate prior authorization and claims payment systems, health plans can identify FWA sooner than ever before. These systems leverage advanced algorithms and real-time data analysis to detect unusual patterns and anomalies that require further investigation, potentially preventing fraudulent activities before they even happen. For example, if a provider consistently bills for services that are statistically unusual compared to peers, this could trigger an alert much more quickly than old-fashioned reactive claims data mining that payors previously relied on, allowing them to begin the investigation sooner. This proactive approach helps in preventing losses rather than just detecting them after the fact.

AI can significantly enhance FWA investigations and reporting in other ways as well. It can quickly analyze large data sets and reduce the time investigators spend manually analyzing the data. AI has been shown to complete certain analytics tasks with a high degree of accuracy,1 which can help reduce human error in reporting. AI can also facilitate better collaboration between different departments and organizations by integrating data from various sources. This holistic view can help enhance the overall investigation process and help ensure that all relevant information is considered. When payors conduct a holistic investigation, they are better able to mitigate the true root cause of the issue and thus reduce the probability of future recurrence.

AI can also play a crucial role in mitigating FWA even after it occurs by enhancing some key processes within the investigation and reporting phase. AI can assist in the recovery of funds lost to FWA by identifying the most effective recovery strategies. It can prioritize cases based on the likelihood of successful recovery and suggest optimal approaches for each case. Based on the analysis of past FWA incidents, AI can suggest adjustments to policies, procedures, and controls to help mitigate the risk of similar incidents in the future. This proactive approach helps in strengthening the overall system. AI can identify common patterns and tactics used in FWA and help develop targeted training programs for staff. By educating employees on the latest FWA schemes and prevention techniques, organizations can reduce the likelihood of future incidents.

Providing Human Oversight for AI Strategies

While AI excels at analyzing data and identifying patterns, complex decision making often requires human judgment, so it is important that AI be implemented safely with human involvement and oversight. Humans can consider context, nuances, and ethical implications that AI might not fully grasp. AI can flag potential FWA cases, but interpreting these results and determining the appropriate actions often requires human expertise. For example, human investigators need to assess the flagged cases to confirm whether they truly represent FWA. While AI can learn and adapt, human intuition and innovative thinking are invaluable. AI is a powerful tool that can greatly enhance FWA prevention and detection, but it works best in collaboration with human expertise. The combination of AI’s analytical capabilities and human judgment helps create a robust system for tackling FWA effectively.

How Forvis Mazars Can Help

AI is a game changer in the fight against fraud, waste, and abuse. By harnessing its power, the healthcare industry can detect and prevent FWA faster and more efficiently than ever before. More importantly, they can better predict FWA before it occurs, helping transform anti-FWA programs from reactive to proactive. If you would like to learn more about how our team can help guide your organization in implementing a safe AI framework or improving your anti-FWA program, please reach out to a professional at Forvis Mazars.

  • 1“Human Error Drives Most Cyber Incidents. Could AI Help?” hbr.org, May 3, 2023.

Related FORsights

Like what you see?
Subscribe to receive tailored insights directly to your inbox.