Medicare Advantage Fraud Enforcement In 2026: What Recent Settlements Reveal About The Limits Of Data-Driven False Claims Act Cases

Key Takeaways

1. Data may increasingly determine where Medicare Advantage investigations begin, but not necessarily where they end. Analytics can identify at scale, but understanding whether those patterns reflect fraud, legitimate operational differences, or something in between generally requires additional context.
2. Recent Medicare Advantage cases illustrate the continuing importance of what happened behind the data. The Kaiser, Aetna, and The Villages Health resolutions involved very different paths to enforcement, but each emphasized internal processes, documentation, decision-making, and what individuals within the organization knew, not statistical anomalies alone.
3. The emerging enforcement model may be increasingly hybrid, and compliance programs should be as well. As DOJ, relators, and others make greater use of analytics, organizations have an opportunity to use those same tools proactively, paired with the operational and clinical expertise necessary to investigate and respond appropriately to what the data reveals.

Over the last several months, there has been no shortage of commentary about the Department of Justice’s (DOJ) Fraud Oversight through Careful Use of Statistics (FOCUS) initiative and the rise of data-driven False Claims Act (FCA) investigations. DOJ has made clear that it is increasingly interested in sophisticated analytics, statistical models, and “data miner” relators who use large public datasets to identify potential fraud.

For Medicare Advantage organizations, the implications appear obvious. Medicare Advantage is one of the most data-rich programs in federal healthcare. Risk-adjusting diagnoses affect beneficiary risk scores. Risk scores affect capitated payments from the Centers for Medicare & Medicaid Services (CMS). Utilization patterns affect medical costs and profitability. Star Ratings affect quality bonus revenue and enrollment growth. Value-based arrangements, delegation models, and risk-sharing contracts create additional financial incentives for plans, providers, and vendors. In other words, nearly every aspect of the Medicare Advantage ecosystem generates data that can be measured, compared, and analyzed. As a result, analytics can identify coding patterns, utilization trends, payment anomalies, and operational outliers on a scale that would have been unimaginable a decade ago.

Many commentators have therefore focused on whether data miners will replace the traditional whistleblower.

That is certainly part of the story, but it may not be the entire story.

While it is still too early to know precisely how data-driven enforcement efforts will reshape the Medicare Advantage landscape, it seems increasingly likely that “data,” broadly defined, will play a growing role in how cases are identified, investigated, and pursued. Less clear, however, is whether data alone can generate and sustain the kinds of Medicare Advantage False Claims Act cases that have historically produced the government’s largest recoveries.

If anything, recent cases suggest that while data may increasingly determine how investigations begin, individuals with inside information often remain critical to understanding the “how” and “why.” Data identifies the anomaly; insiders explain the conduct.

Medicare Advantage Is Tailor-Made for Data-Driven Fraud Investigations

Few healthcare programs are as susceptible to statistical scrutiny as Medicare Advantage. Plans, providers, consultants, relators, and government investigators can compare things like:

• Diagnosis prevalence and coding patterns
• Utilization rates and care-management trends
• Prior authorization activity and denial rates
• Chart-review and in-home assessment activity
• Star Ratings performance and quality metrics
• Broker and marketing enrollment patterns
• Year-over-year operational and financial trends

As DOJ’s FOCUS initiative recognizes, those kinds of analyses can help identify organizations that appear materially different from industry benchmarks.

But identifying a pattern and proving fraud are not the same thing. One of the central challenges with data-driven enforcement is that being different from one’s peers does not inherently mean anything improper occurred.

Consider two physician groups. One captures diabetes complications at significantly higher rates than the other. That difference might reflect unsupported coding. But it could also reflect a sicker patient population, stronger chronic care management, more robust provider education, more thorough documentation practices, better coding accuracy, or simply more diligent capture of existing conditions.

The same is true for many of the other metrics increasingly discussed in Medicare Advantage enforcement. An organization that looks different from its peers may be engaging in problematic conduct. But it also may have a sicker patient population, a more effective quality program, a different provider network, stronger care-management initiatives, more sophisticated documentation practices, more effective marketing strategies, or distinctive contractual arrangements with providers and vendors. Data can reveal the existence of a pattern. It typically cannot explain the reason for it.

Put differently, Medicare Advantage analytics are exceptionally good at identifying organizations that warrant a closer look. They are often far less effective at distinguishing between a legitimate operational difference and fraud. That distinction requires additional context, documents, and, in many cases, people who can explain what was actually happening behind the numbers.

What the Recent Medicare Advantage Docket May Tell Us About What’s Coming Next for Medicare Advantage Compliance

Three 2026 Medicare Advantage resolutions illustrate this interplay.

Kaiser Permanente (January 2026). Kaiser Permanente affiliates agreed to pay $556 million to resolve risk-adjustment allegations. DOJ alleged that Kaiser increased Medicare Advantage reimbursements by developing mechanisms to identify potential diagnoses from patients’ historical medical records and then sending provider “queries” encouraging physicians to add those diagnoses through post-visit addenda. These allegations show us that the tools and outcomes measurable by data are not inherently problematic; rather, the potential concern presents in how those tools were used, what incentives existed, what safeguards were in place, and what decision-makers allegedly knew about the accuracy of the resulting diagnoses. Those are not questions that data alone can answer. Notably, what ultimately became the “Kaiser” resolution did not begin as a single whistleblower action. Rather, multiple qui tam complaints were filed by six relators over a number of years. The government later partially intervened, and the actions were consolidated into a single matter, with two relators ultimately sharing approximately $95 million of the recovery.

Aetna (March 2026). Aetna agreed to pay approximately $117.7 million to resolve allegations that it failed to delete unsupported risk-adjusting diagnoses identified through chart review practices and failed to delete certain unsupported morbid-obesity diagnoses. The case originated with a former risk-adjustment coding auditor. A data analyst might have been able to identify unusual diagnosis-submission or deletion patterns. The relator, however, allegedly had visibility into the coding-review process itself, including what chart reviews identified and how the organization responded. That type of information shapes questions about knowledge and intent.

The Villages Health (August 2026). The Villages Health agreed to a $541.5 million settlement relating to alleged unsupported diagnoses submitted to Medicare Advantage organizations, which we previously reported on in August 2026 . Unlike many large FCA matters, The Villages did not originate with a qui tam relator. Instead, DOJ credited the company for self-disclosing the conduct after an internal investigation identified concerns regarding diagnosis coding and documentation practices.

The Villages may represent an important glimpse into how advanced analytics, auditing, and internal compliance reviews could shape future enforcement. Rather than a whistleblower identifying the issue, the organization’s own review process reportedly uncovered it first. Yet even The Villages reinforces the broader point. The core allegations did not turn on statistical anomalies alone. They involved operational questions regarding record amendments, documentation practices, provider involvement, approval processes, and the clinical support for submitted diagnoses. Even when data helps identify an issue, understanding that issue still requires examining what actually occurred inside the organization.

What the Government Must Prove in Medicare Advantage FCA Cases

The distinction is important because the False Claims Act requires more than proof that a claim was inaccurate. To establish liability, the government or relator generally must prove falsity, materiality, and scienter, meaning that the defendant knowingly submitted or caused the submission of false claims.

In the Medicare Advantage context, scienter is often the battleground. Data can identify unusual patterns, coding spikes, higher-than-expected diagnosis prevalence, elevated denial rates, or other anomalies. What it often cannot establish is what the organization knew about those patterns or why they occurred.

That challenge helps explain why a number of purely data-driven FCA cases have struggled in court. Courts have frequently expressed skepticism when relators attempt to infer fraud primarily from statistical analyses and public information without firsthand knowledge of the underlying operations, documentation, or decision-making. Datasets rarely reveal whether internal audits identified a problem, whether employees raised concerns, whether the organization investigated those concerns, or whether leadership knowingly disregarded contrary information.

Stated differently, data is often powerful evidence of what happened. It is frequently much weaker evidence of what people knew.

How DOJ’s FOCUS Initiative Will Shape the Future of Medicare Advantage FCA Enforcement

It remains to be seen exactly how DOJ’s FOCUS initiative and other data-driven enforcement efforts will reshape the Medicare Advantage FCA landscape. Many of the settlements discussed above originated years ago, before the government’s recent embrace of analytics and before the rapid evolution of artificial intelligence (AI)-enabled review tools. As a result, today’s enforcement examples are not necessarily a perfect predictor of tomorrow’s cases.

Still, if history is a useful reference point, the lesson from those resolutions is not that data will replace whistleblowers. Rather, it suggests a more nuanced future in which analytics and insider information increasingly complement one another.

If that proves correct, the Medicare Advantage FCA cases of the future may look different at the front end than the cases of the past. They may begin with statistical signals rather than human complaint. But when it comes to building and proving FCA cases, data and insider information may increasingly work hand-in-hand: data highlighting where investigators should look and firsthand knowledge helping explain what they find once they get there.

What Should Medicare Advantage Organizations Do to Prepare for Data-Driven Enforcement?

For Medicare Advantage organizations, there is also a practical takeaway. If DOJ, relators, and data-mining firms are increasingly using sophisticated analytics to identify unusual patterns, organizations should consider whether they are using similar tools to monitor their own operations. The same analytics that can identify potential concerns for regulators or relators can also help organizations identify compliance risks before they become the subject of an investigation.

That said, and as is always the case, organizations should approach those efforts thoughtfully. One reason scienter remains such a critical element of the False Claims Act is that knowledge can create obligations. An organization that uncovers credible red flags through data analysis must be prepared to investigate, document, remediate, and, where appropriate, take corrective action. Simply identifying a potential anomaly without addressing it can create its own set of risks.

The challenge, therefore, is not whether to use data, but how to use it responsibly.

If the future of Medicare Advantage FCA enforcement is indeed a hybrid model, the most effective compliance programs will likely be hybrid as well: combining data-driven monitoring with the operational, clinical, and compliance expertise necessary to understand what the data actually means and to act on it appropriately.

To explore additional FCA settlements and enforcement trends in the Medicare Advantage space, visit our Healthcare Fraud & Abuse Resource Center for a searchable database of settlements from the last decade. If you have questions about data-driven enforcement, Medicare Advantage compliance, or the DOJ’s FOCUS initiative, please contact a member of the Bass, Berry & Sims Healthcare Fraud & Abuse Task Force.

The content of this article is intended to provide a general guide to the subject matter. Specialist advice should be sought about your specific circumstances.