Data prioritization, hybrid cloud help HHS auditors uncover fraud
- By Sara Friedman
The inspector general at the Department of Health and Human Services works to find waste, fraud and abuse, but outdated data collection methods had created roadblocks. To sift through data from the Center for Medicare and Medicaid Services, for example, OIG employees visited CMS offices monthly to pick up datasets and take the information back to their office for analysis.
The IG’s migration to the cloud, however, has made remote exchanges of data and new analytical capabilities simpler. And with a data lake, the IG can store its unstructured data while still making it searchable.
When CTO Evan Lee joined the IG’s office in 2016, he realized the average age of more than 90 legacy applications was 12 years and that a traditional data center wasn’t going to be able to support his office’s data analytics needs. The team needed some help from the cloud.
“A hybrid infrastructure creates connectivity between our data center and a cloud service provider,” Lee told GCN. It lets OIG use the existing resources in the data center “and take advantage of the scalability and elasticity of the cloud,” he said.
Working with Excella Consulting, Lee’s team tackled the biggest pain points that would provide the largest benefit to their investigative work. They started by creating a central dashboard through the Looker analytics platform so Lee and his managers could set access controls for specific datasets.
The Amazon Redshift data warehouse provided the foundational structure of the database, which included operational information on audits, evaluations and investigations. Through agile development and data governance policies, the team created strategic roadmaps for different data components, technologies and tools.
“We are looking into … the data that they use to audit providers and patient information, to analyze and determine the different subsets,” said Claire Walsh, Excella's data and analytics practice lead at Excella. “We are targeting our work to look at the common data elements and the most engaged users in specific areas.”
As more data is moved into the platform, Lee said his office will be able to build a more complex fraud analytics model with more “storage, processing and computing power” to improve accuracy.
“The fraud models are looking for outliers, but we know that there are a lot of fraud perpetrators out there as well as well-educated doctors and pharmacists who have access to CMS for their services,” Lee said. The more accurate the model, the easier it will be to find the fraud outliers.
Once investigators can get a better idea of their data processing needs, Lee said he expects machine learning to play a role in the investigation process. But for now, the priority is the categorization and prioritization of data to create a foundation for the future.
Sara Friedman is a reporter/producer for GCN, covering cloud, cybersecurity and a wide range of other public-sector IT topics.
Before joining GCN, Friedman was a reporter for Gambling Compliance, where she covered state issues related to casinos, lotteries and fantasy sports. She has also written for Communications Daily and Washington Internet Daily on state telecom and cloud computing. Friedman is a graduate of Ithaca College, where she studied journalism, politics and international communications.
Friedman can be contacted at firstname.lastname@example.org or follow her on Twitter @SaraEFriedman.
Click here for previous articles by Friedman.