Venil MenonHealthcare claims constitute the majority of fraudulent insurance claims in the United States, and the fraud occurs on a regular basis. The U.S. Department of Justice (DOJ) recently reported recovery of nearly $2 billion in healthcare fraud settlements in 2015 under the False Claims Act.a One instance of healthcare billing fraud, reported in November 2015, amounted to $600 million, according to the DOJ.b

These cases are only the tip of the fraud, waste, and abuse (FWA) iceberg. The FBI estimates annual healthcare fraud in the United States to be an $80 billion problem, with federal programs such as Medicaid and Medicare most commonly victimized. A large proportion of fraud cases involve Parikshit Shethkickbacks for valueless medication and other hospitalization services, as well as fraudulent Medicare claims. In 2015, the Centers for Medicare & Medicaid Services (CMS) revoked 28,000 provider enrollments in the Medicare program and deactivated 470,000 enrollments.c

Big Data: A Challenge and Opportunity

Insurers and federal agencies can use big data to combat FWA in health care, but access to large volumes of healthcare data poses a challenge as much as an opportunity for them. The current volume of data is growing at a staggering pace, with nearly 45,000 new providers applying for Medicare enrollments every month, adding to an already vast store of data that require analysis.d Federal agencies and insurers alike require big data analytics to be able to analyze claims data or social media data (such as tweets and content posts) to identify fraudulent activities; spot hidden claim duplicates; detect zero-value medical events; and assess the probability of fraud within specific provider groups, care settings, regions, or patient populations.

T-MSIS Naturally Extends to Big Data Analytics

The Transformed-Medicaid Statistical Information System (T-MSIS), a national database that contains detailed information about Medicaid and the Children’s Health Insurance Program (CHIP), provides a basis for addressing this challenge. CMS recently made the transition to T-MSIS in collaboration with Medicaid and CHIP Business Information Solutions (MACBIS) data stakeholders.

T-MSIS shows how healthcare big data can be aggregated and managed to drive deep analytics and powerful reporting. The platform will benefit insurers and federal agencies in multiple ways:

  • Allowing states to analyze data in the national repository along with the data available in their own repositories
  • Enhancing FWA detection and prevention by analyzing large volumes of healthcare data along with other information present in CMS repositories
  • Reducing the number of data requests and reports that CMS requires from various states, as already available T-MSIS data will be used by CMS to derive these reports

Big data analytics naturally extend to the T-MSIS platform to help identify suspicious patterns within large healthcare datasets. With the big data collected from T-MSIS, CMS also is applying analytics to all fee-for-service insurance claims. The analytics system identifies unusual and mistrustful billing patterns, helping insurers trigger immediate actions to prevent claims fraud. This capability has helped CMS save $210.7 million to date.e

Operational Challenges in Leveraging Big Data for FWA

In spite of federal initiatives like T-MSIS, reports indicate that fewer than half of insurance agencies are aggressively trying to prevent FWA explicitly or implicitly with proactive big data analytics programs. With limited resources to tackle the increasing volume of provider data and the associated healthcare big data, insurers continue to be plagued by the following operational challenges.

Limited ability to manage unstructured data. Unstructured data from disparate sources such as documented notes from insurance adjusters present a fraud risk. To leverage fraud analytics solutions effectively, insurers need to collate historical data from the internal sources and digital footprint as well as demographics data from external sources.

Legacy data infrastructure. Most insurers are using legacy IT systems, which take longer to process huge amounts of data and make it difficult to predict all types of FWA. The fragmentation of IT infrastructure results in inconsistent data, which might lead to inaccurate fraud predictions.

Data quality issues. Fraud analytics engines use historical and existing data to identify and prevent health insurance fraud. Data quality is of high importance when leveraging big data analytics to identify potential fraud. Fraud analytics engines might function improperly or stop functioning if the dataset is not clean, or it might generate false positives. Data quality thus presents a challenge when combining both external and internal data.

Analytics skill shortage. Unqualified personnel, incorrect decision making, and lack of training are the major challenges for insurers in leveraging effective analytics for FWA.

In spite of these challenges, healthcare insurers and federal agencies have overwhelming reasons and proof to turn to big data analytics for FWA prevention. Big data technology alone cannot prevent FWA; however, strategic use of big data analytics technology can root out dubious claims and bills from the pile of legitimate ones. Once these technology challenges are addressed, we can expect to see big data analytics being used extensively by health plans, not just to root out inefficiencies and waste, but also to prevent large-scale healthcare fraud.

Insurers, on their part, need to use specialized teams to help upgrade their IT infrastructure and to support ingestion and processing of huge volumes of data. Security and privacy of patient data should be top-of-mind when integrating data from a variety of sources. By taking an enterprise-wide approach to big data management, and supporting it with the right kind of training and technology, healthcare organizations can successfully mitigate business risks and lower the probability of FWA.

Vinil Menon is the chief technology officer of CitiusTech, Princeton, NJ.

Parikshit Sheth is a healthcare consultant of CitiusTech, Princeton, NJ.


a. U.S. Department of Justice, “Justice Department Recovers Over $3.5 Billion From False Claims Act Cases in Fiscal Year 2015,” Dec. 3, 2015. 

b. U.S. Department of Justice, “Five Individuals, Including Two Doctors, Charged in Kickback Schemes Involving nearly $600 Million in Fraudulent Claims by Southern California Hospitals,” Nov. 24, 2015. 

c. U.S. Department of Health & Human Services, “Departments of Justice and Health & Human Services announce over $27.8 billion in returns from joint efforts to combat health care fraud,” March 19, 2015.  

d. Glanz, B., “Fraud, Waste, and Abuse: Feds Remain on the Defensive,” GovTechWorks, Oct. 20, 2015.

e. U.S. Department of Health & Human Services, Statement by Shantanu Agrawal, MD, Deputy Administrator and Director, Center for Program Integrity, on the Use of Data to Stop Medicare Fraud, Testimony before Committee on Ways & Means Subcommittee on Oversight, United States House of Representatives, March 24, 2015.

Publication Date: Thursday, April 07, 2016