tuva-health/tuva

Synthetic data enhancement: add ambiguous professional/institutional claims

Closed this issue · 0 comments

We have seen real claims datasets with claims that are ambiguous in that sense that they have both professional and institutional data elements. To show this real world data quality problem in Tuva synthetic we can add claims with that feature.

Currently in Tuva Synthetic we have:

  • 8,626 institutional claims (9.9%): they all have only institutional data elements and no professional data elements
  • 78,501 professional claims (90.1%): they all have only professional data elements and no institutional data elements

We could add more new claims that have both institutional and professional data elements.