Offline
Data quality

Master data & EMPI

Patient, provider, and facility golden records. Duplicate detection, survivorship rules, and stewardship queue — measured.

EMPI records
14.2 M
Duplicate rate
0.42%
Steward queue
184
Match precision
99.6%

Stewardship queue · likely duplicates

  • Maria Gonzalez / Maria L. Gonzales · DOB 1978-04-12
    match score 0.94
  • James Patel / Jim Patel · same MRN root
    0.91
  • Anh Nguyen (M) / An Nguyen (M) · same address
    0.88
  • Robert Smith Jr / Robert Smith II
    0.82 — needs human

Survivorship rules (excerpt)

  • Legal namefrom gov-ID source
  • Phone / addressmost recent verified
  • DOB / sexconsensus across ≥ 2 sources
  • Allergiesunion, manual de-dup
  • Insurancemost recent payer 270/271

Reference & code-set health

ICD-10-CM2026 release · in sync
SNOMED CT USMar 2026
LOINC2.81
RxNormweekly delta clean
NPI registrysynced 4h ago