Payers Are Approaching a Moment of Reckoning on Fraud, Waste, and Abuse
By Ketan Patel, MD
Ketan Patel, MD is chief medical officer of SyTrue of Stateline, NV.
Payers are poised to face a new operating environment with significantly more scrutiny over fraud, waste, and abuse (FWA) in the wake of COVID-19.
Two years ago, the federal government created the Medicare Advantage (MA) Risk Adjustment Data Validation (RADV) program to beef up audits of MA insurers. For 2022, CMS also doubled its budget for fraud, waste, and abuse (FWA) investigations, and the Department of Justice just announced charges against 21 defendants accused of various healthcare fraud schemes involving the COVID-19 pandemic. Meanwhile, payers are working to reconcile billions of dollars in COVID-related medical expenses and correctly identify risk for the surging number of long COVID patients.
These factors have converged to generate significant potential headwinds for payers and will create the following two new realities:
- Payers will be forced to sift through increasingly huge volumes of clinical records to identify potential fraud and waste, as well as confirm bill accuracy to properly compensate providers.
- At the same time, as we head into the third year of the pandemic, payers will uncover an unprecedented amount of FWA related to COVID-19.
How successfully payers manage these challenges will be determined by their ability to replace time-consuming and expensive manual processes with artificial-intelligence-based tools that comb patient records to identify potential fraud, assess patient and population risk, and confirm payment accuracy.
In the past, payers depended on expensive and time-consuming chart reviews to find and extract key unstructured data from patient records, such as information that reveals the need (or lack thereof) for a patient to undergo various COVID-related tests. More recently, though, payers have turned to natural language processing (NLP) as an alternative to manual chart reviews. NLP is an AI-based technology that enables computers to “read” and understand text by simulating humans’ ability to interpret language, but without the limitations of human bias and fatigue.
With NLP, payers can retrospectively analyze longitudinal health data to find a particular piece of clinical information about a single patient or identify subsets within populations that require further exploration. Given today’s environment of increased FWA scrutiny, NLP is poised to play an increasingly important part in helping payers pinpoint instances of FWA.
The following are three ways payers can leverage NLP to improve FWA detection:
- Detect patterns. In cases of FWA, there is often a pattern of repeatability in the data, such as a large number of patients meeting the same prior authorization requirements. NLP helps payers detect these patterns that lack the natural variability found in legitimate patient records.
- Identify outliers. In the same respect, NLP can help payers spot unusual data that may be representative of fraud, such as expensive tests for which there is no medical necessity. With its ability to accurately analyze unstructured data to identify anomalies within records, NLP can quickly verify the presence, or lack of, critical data.
- Improve scale. While even the most hard-working humans possess limitations on their ability to perform a high amount of chart reviews in a narrow timeframe, NLP automates the process, enabling substantial improvements in scalability. Because some complex medical records may consist of thousands of pages, NLP can drive significant savings in time and money in reviews.
For payers, the time to prepare for increased FWA scrutiny is now.