top of page

Can Artificial Intelligence Help Us To Detect Health Care Fraud?

Any reader of the Allegiant Experts Blog is well aware of how on top we stay of health care fraud incidents in the United States. Covering a minimum of one story per week doesn’t even come close to truly exposing the mass amount of fraudulent activity that takes place in the medical community. Most specifically, Medicaid and Medicare are victims of health care fraud on an all-too-regular basis.

Of course, our blog has also reported on the wide spread prevention tactics carried out by law officials. In many cases, fraudsters have been brought to justice and greater light has been shone on the nationwide problem of health care fraud. Nevertheless, more needs to be done to both diminish instances of fraud and eliminate them altogether. And while the latter aspiration may be far-fetched, modern technology may just provide a much-needed glimmer of hope.

Researchers are teaching machines to detect Medicare fraud.

Last week, EurekAlert! (“The Global Source of Science News”) released a report detailing the work of researchers from Florida Atlantic University’s College of Engineering and Computer Science. They are working on developing a program that can help human auditors and investigators check the seemingly countless claims that Medicare receives.

The program, known as Medicare Part B, is being designed to detect specific patterns that could indicate foul play or fraudulent behaviors. “Furthermore, according to the U.S. Department of Justice, right now fraud enforcement efforts rely heavily on health care professionals coming forward with information about Medicare fraud,” notes EurekAlert!

“A study published in the journal Health Information Science and Systems is the first to use big data from Medicare Part B and employ advanced data analytics and machine learning to automate the fraud detection process,” explains the report, “Programming computers to predict, classify and flag potential fraudulent events and providers could significantly improve fraud detection and lighten the workload for auditors and investigators.”

37 millions cases have been researched.

Researchers from FAU’s Department of Computer and Electrical Engineering and Computer Science have been examining Medicare Part B data for years now. The focus has been on detecting fraudulent provider claims using upwards of 37 million cases for their research. “For the study, the researchers aggregated the 37 million cases down to a smaller dataset of 3.7 million and identified a unique process to map fraud labels with known fraudulent providers,” says EurekAlert!

Medicare Part B data includes provider information, average payments and charges, procedure codes, the number of procedures performed and the medical specialty, or provider type. Researchers used the National Provider Identifier (or NPI, which is a single identification number issued by the federal government to health care providers) to match fraud labels to the Medicare Part B data.

“Researchers directly matched the NPI across the Medicare Part B data, flagging any provider in the ‘excluded’ database as being ‘fraudulent,’” explains the report. Dr. Taghi M. Khoshgoftaar is the Motorola Professor in FAU’s Department of Computer and Electrical Engineering and Computer Science. He has great faith in Medicare Part B’s ability to detect health care fraud.

“If we can predict a physician’s specialty accurately based on our statistical analyses, then we could potentially find unusual physician behaviors and flag these as possible fraud for further investigation,” he is quoted as saying in the report.

Are you an attorney trying a health care fraud case?

Please don’t hesitate to contact Allegiant Experts to find out how our clinical expertise may help you. Call us at 407-217-5831 or email us at

1 view0 comments


bottom of page