The U.S. District Court for the Eastern District of Tennessee answered what it acknowledged was a novel question: whether statistical sampling and extrapolation are appropriate to establish liability under the False Claims Act (FCA). The court found the government could extrapolate from a sample of patient records to prove FCA liability. While the court’s decision approved the use of sampling, it emphasized the defendant could challenge the government’s methodology and that the government was not using sampling to prove all of the elements of the alleged FCA violations.

The decision involves Life Care Centers of America, Inc. (Life Care), which operates more than 200 skilled nursing facilities and is alleged to have billed the government for unnecessary care from 2006-2012. Rather than examine all of the potentially false records, which total more than 54,000 patient admissions (and 150,000 claims), the government plans to perform a medical review of a sample of 400 patient admissions. The government intends to extrapolate the results of its review of this sample to establish liability across the full universe of patient records.

Life Care moved for summary judgment regarding any claims that were “unidentified” or not part of the 400 sampled claims. According to Life Care, the government’s approach violated its due process rights and impermissibly shifted the burden of proof to Life Care. Life Care argued sampling could not establish all the required elements of a FCA violation. It contended that sampling does not account for differences across patients and that a record-by-record review is necessary. Life Care also argued the government could not show it possessed the necessary state of mind—scienter—by extrapolating from a sample.

In response, the government argued statistical sampling is an established method of proof in complex litigation that is widely accepted for determining overpayments in government benefits programs. Furthermore, the government argued the FCA’s requirement of proof of a false claim did not preclude the use of statistical sampling.

In agreeing with the government, the court found the government potentially could establish the FCA elements for each of the 150,000+ claims, but that would be too burdensome (for both the government and the court): “The purpose of the FCA as well as the development and expansion of government programs as to which it may be employed support the use of statistical sampling in complex FCA actions where a claim-by-claim review is impracticable.” The court stated Congress had not prohibited the use of sampling in FCA cases and that for the court to do so would embolden “potential perpetrators of fraud” and “open the door to more fraudulent activity.”

The court determined Life Care’s due process rights were protected sufficiently because it can present evidence regarding differences in the claims and challenge the government’s methodology and expert witness. Moreover, because the government represented that it did not intend to rely on sampling to establish scienter, the court ruled that whether the government can meet this element would be determined by the evidence presented at trial.

On Oct. 10, 2014, Life Care asked the District Court to certify the ruling as appropriate for interlocutory appeal. If the District Court does so, Life Care will ask the 6th Circuit Court of Appeals to review the decision. In the meantime, the government may rely on this case to support its use of extrapolation to prove liability in FCA cases.