Data analysts know that all data is dirty. Although numerous services offer data cleaning and harmonization, the accuracy of many of them is usually too poor to make them useful. According to Amit Garg, CEO and co-founder of HiLabs, even AI-based solutions produce too many false positives—a problem his company has solved by working with business domain experts and creating healthcare-specific ontologies.
Sources of errors and gaps in data are legion. A web site might list a doctor as being in-network, but the payer doesn’t actually cover them. A data entry clerk might switch two fields when putting information into a system. Patients forget what doctors they saw or what medications they’re taking and fail to report it. Data from diverse sources may be coded differently and have incompatible field names.
Garg founded HiLabs as a solution to dirty data, saying that the founders started out hoping to use AI to analyze the data but found that incoming data was “garbage.” The use of domain experts was of critical importance because when using unsupervised AI, “You don’t know what you’re looking for.”
With the combination of machine and human intelligence. HiLabs achieves more than 95% accuracy.
Watch this short video to hear Garg’s description of the problem of dirty data, use cases for their technology, and how HiLabs wins customers to fix the problem.
Learn more about HiLabs: http://www.hilabs.com/
Listen and subscribe to the Healthcare IT Today Interviews Podcast to hear all the latest insights from experts in healthcare IT.
And for an exclusive look at our top stories, subscribe to our newsletter.
Tell us what you think. Contact us here or on Twitter at @hcitoday. And if you’re interested in advertising with us, check out our various advertising packages and request our Media Kit.
