Published June 15, 2026 | Version v1.0.0

EHR Data Density Index (EDI): PySpark pipeline for utilization archetypes and data-density analysis

Description

PySpark/Databricks pipeline for GMM-4 EHR utilization archetypes, four-domain density vectors, and Charlson Comorbidity Index association analyses on OMOP CDM data. Includes cohort_1 manuscript pipeline, cohort_2a/2b validation inference, and edi_* artifact layout. Code snapshot at first manuscript submission.

Files

abhatia08/data-density-v1.0.0.zip

Files (155.8 kB)

Name Size Download all
md5:64136f343802c6639c1b0400dff4e460
155.8 kB Preview Download

Additional details

Related works