In this paper, we review a narrow slice of messy data in healthcare: provider data that appears in medical claims datasets. By presenting findings from a review of a nationally representative sample of medical claims records from a variety of contributor organizations, we hope to guide others in the questions they should be asking of their own data processes. We highlight some of the common issues and potential mitigation strategies to improve data gaps, with our discussion organized as follows:
- Study background: the importance of clean data
- Audit process and findings
- Implications and next steps
- Additional background