According to the Department of Health and Human Services, more than 400 defendants in 41 federal districts were charged with participating in fraud schemes involving about $1.3 billion in false billings to Medicare and Medicaid in 2017 alone.
Now research suggests that artificial intelligence may help detect Medicare fraud in the home health and hospice sector as Home Health Care News reports.
A research team from Florida Atlantic University used algorithms to identify potentially fraudulent Medicare Part B claims in data supplied from the Centers for Medicare & Medicaid Services (CMS) data ranging from 2012 to 2015. Among fraudulent activities flagged were patient abuse or neglect and billing for services that were never rendered.
The study is viewed as just the tip of the iceberg for what machine learning can do in this field. “There are a lot of things we can do both from the data side and algorithm side — different ways of looking at data or using different algorithms to better predict fraudulent cases,” Taghi Khoshgoftaar, Florida Atlantic University director of Data Mining and Machine Learning Lab in the Department of Computer and Electrical Engineering and Computer Science, said to Home Health Care News. “This is very important not just for Medicare fraud, but also for other domains like insurance fraud, financial fraud and transaction fraud.”
Spending less funding on fraud detection could mean more patient resources, added Khoshgoftaar. “It’s good to use a tool like AI that is very effective in detecting fraudulent cases.”
“We need to be cognizant that every innovation has downsides … that need to be managed… [AI] is not a panacea. It doesn’t solve every problem.”
Experts warn that machine learning should be used with an understanding of its limitations for home health care fraud detection.
“We need to be cognizant that every innovation has downsides … that need to be managed,” Danielle Pierotti, RN, Ph.D., acting president and CEO of industry associations ElevatingHOME & VNAA told HHCN. “… [AI] is not a panacea. It doesn’t solve every problem.”
These problems could include patient record labeling errors and the oversensitivity that results in the conflating of minor documentation flaws with deliberate fraud.
