Healthcare data today remains a collection of quasi-structured data, ad-hoc sets of files, and customized file formats from hundreds of vendors and providers. While this data can be difficult to work with, to healthcare companies the value stored in this data is massive. Health insurance companies have typically used large numbers of staff to extract this data in a process that is prone with delays, errors, and incompleteness. At Clover, we have built an automated parsing framework to ingest the diversity of healthcare data and deliver improved efficiency to our insurance operations.
Leveraging this parsing framework has enabled us to uncover ways to improve patient outcomes and decrease medical cost. In this presentation, we'll demonstrate the technologies used to build our parsing system that yields increasing value from complex healthcare data. We'll show how this a system balances both flexibility and strict quality controls to deliver a foundational data platform from which Data Science and Operation teams can build other data structures on top of. And finally, we'll discuss the strategies used to monitor and proactively respond to data quality issues.
Chris Hartfield is a senior data engineer at Clover Health, where he is using analytics to improve healthcare outcomes for the Medicare community. Prior to joining the company, Chris was part of the engineering team at Poplicus, a organization that creates proprietary analytics from big data in the public sector. While there, he was responsible for the search logic and proprietary metrics to detect trends and insights into public spending.
Chris also holds a Bachelor’s degree in Biomolecular Engineering from the University of California, Santa Cruz.