Stopping Healthcare Fraud in Its Tracks
May 06, 2019
It is no secret that rising healthcare costs are a widespread concern across the country. The Centers for Medicare and Medicaid Services (CMS) estimate that national health spending reached $3.5 trillion in 2017, accounting for 17.9 percent of GDP. By 2026, it is projected to reach $5.7 trillion, accounting for 19.7 percent of GDP, or one fifth of the entire economy. This projected growth is largely attributed to the expected shift from private insurance to Medicare due to the aging population and increases in prices for medical goods and services. Some factors that are undoubtedly contributing to the rise in healthcare costs are fraud and abuse. An estimated 10 percent of healthcare spending, or $350 billion in 2017, is wasted due to fraud and abuse. The massive scale of this problem should make it a priority for health systems and government agencies who oversee this sector. Using analytics to process the enormous amounts of available data to find fraud and abuse can have a huge impact by reducing costs and improving care.
The spectrum of fraud and abuse in healthcare can range from unintentional mistakes in coding and billing, to wasteful diagnostic tests or procedures, to outright falsification of medical records and claims that result in improper payments. These behaviors either directly or indirectly result in unnecessary costs to payers and patients. Some examples of common abusive or fraudulent behaviors include:
- Billing for medically unnecessary services, including misrepresenting non-covered treatments as medically necessary or falsifying a diagnosis to justify unnecessary services
- Billing for services not rendered
- Upcoding (billing for more expensive services than were provided)
- Unbundling (billing each step of a procedure as if it were a separate procedure)
- Waiving patient copays/deductibles and overbilling insurance carriers
- Billing patients for higher copays than required by benefit plans
- Kickbacks for patient referrals
- Medical identity theft
As organizations adopt electronic systems for medical records, claims, billing, and scheduling, more and more data become available. Using analytics to comb through this wealth of information, organizations can much more effectively detect fraud and abuse. Instead of auditors going through the time-consuming and inefficient process of reviewing thousands of claims, automated fraud detection methods using machine learning can extract useful information from large amounts of data by looking for inconsistencies, anomalies, and suspicious patterns. A smaller, focused subset of claims or information can be identified for further scrutiny by an organization, resulting in a much more efficient and cost-effective process.
Not only can analytics help detect fraud, but automated processes can be set up to stop fraudulent claims before payment. This would prevent what is commonly referred to as “pay and chase,” where claims are paid and then an attempt is made to recover the costs after fraud is identified. Experts estimate that only 10 to 20 percent of fraud and abuse is recovered after payments are made. Early detection and risk mitigation can be huge drivers in reducing costs from fraud and abuse by preventing money from walking out the door in the first place.
Healthcare fraud and abuse affects everyone. For consumers, it causes higher premiums and out-of-pocket costs, as well as reduced benefits or coverage. For employers, it increases the cost of providing health insurance benefits to employees. Government spending on healthcare, funded by taxpayers, will also continue to increase as a result. In addition to financial costs, patients who are victims of healthcare fraud or abuse are subject to unnecessary or unsafe medical procedures. Victims of identity theft can have compromised medical records or have stolen insurance information that is used to submit false claims. Analytics can be a powerful tool for organizations to combat healthcare fraud and abuse to identify and prevent fraudulent activity, reducing costs for everyone and improving the quality of care for patients.