Fig. 3: Snapshot of MIMIC-IV on FHIR dataset used in evaluation.
From: SQL on FHIR - Tabular views of FHIR data using FHIRPath
Size and composition of the dataset used for testing. The dataset contains 299,712 patient records, 929,499 clinical encounters, and 461,098,908 observations from 2008 to 2019, all following the FHIR R4 standard. This provides sufficient data to test how well the SQL on FHIR approach works for preparing large clinical datasets for analysis.
